© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6944
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to physics and astronomy, especially those concerning neutron stars, pulsars, and celestial mechanics

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related phrases

    np_token-act-pair-logits · gpt-4o-mini

    astrophysics and physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.67
    Legenda
    -0.50
    átek
    -0.49
    ómica
    -0.49
    ingual
    -0.48
     Northern
    -0.47
    Wut
    -0.47
    beiros
    -0.47
    Diamonds
    -0.47
    mazione
    -0.46
    POSITIVE LOGITS
     تضيفلها
    0.72
    GOTREF
    0.59
    InitVars
    0.58
     TextInputType
    0.56
    abestanden
    0.54
    SafeMath
    0.54
     gynhyrchwyd
    0.54
    PreferredItem
    0.52
    PickerController
    0.52
     Horizonte
    0.51
    Activations Density 2.561%

    No Known Activations