© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11334
    Prev
    Next
    INDEX
    Explanations

    words describing something strange, unsettling, or unnatural that is perceived by the senses.

    oai_token-act-pair · gemini-2.0-flash

    ry/y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     GenerationType
    -0.82
    GenerationType
    -0.81
    ThroughAttribute
    -0.74
     onAnimation
    -0.74
    InjectAttribute
    -0.71
     religieuses
    -0.64
     vectorielles
    -0.63
     typelib
    -0.63
     فريبيس
    -0.62
    DispatchToProps
    -0.61
    POSITIVE LOGITS
    ībā
    0.53
     enough
    0.51
     carried
    0.47
    blatt
    0.47
     favorably
    0.47
     mean
    0.47
     ins
    0.47
     الرخصة
    0.46
     priv
    0.45
     thế
    0.45
    Activations Density 7.360%

    No Known Activations