© 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. 8676
    Prev
    Next
    INDEX
    Explanations

    sensationalist phrases related to government, health, rules, and regulation.

    oai_token-act-pair · gemini-2.0-flash

    terms related to machines

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

    machines

    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
    Geplaatst
    -0.69
    RectangleBorder
    -0.67
     MainAxisSize
    -0.66
    niająca
    -0.63
    ScopeManager
    -0.62
    tahui
    -0.61
    OGND
    -0.60
    enumi
    -0.60
     invokingState
    -0.60
    enumii
    -0.58
    POSITIVE LOGITS
     machines
    0.79
    machines
    0.68
     computers
    0.66
     machinery
    0.65
     Machines
    0.62
    computers
    0.62
     tests
    0.61
     machine
    0.59
     testing
    0.56
    Machines
    0.55
    Activations Density 4.051%

    No Known Activations