© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10423
    Prev
    Next
    INDEX
    Explanations

    mentions of shareable items being "out there"

    oai_token-act-pair · gemini-2.0-flash

    technical terms or coding functions

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

    out

    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
     world
    -1.85
    world
    -1.45
     WORLD
    -1.24
    世界
    -1.22
     World
    -1.21
     worlds
    -1.15
     mundo
    -1.14
    welt
    -1.13
    World
    -1.12
     Welt
    -1.12
    POSITIVE LOGITS
    CloseOperation
    0.59
    lacian
    0.50
     متعلقه
    0.47
     üzere
    0.45
     giacca
    0.44
     balanceOf
    0.43
     arşivlendi
    0.42
     voet
    0.42
    gulier
    0.42
     voeten
    0.40
    Activations Density 3.080%

    No Known Activations