© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10769
    Prev
    Next
    INDEX
    Explanations

    the word "feet" and words associated with injuries.

    oai_token-act-pair · gemini-2.0-flash

    feet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.67
     Jefus
    -1.48
     Efq
    -1.45
     myſelf
    -1.45
     Anſ
    -1.39
     himſelf
    -1.39
     themſelves
    -1.35
     pleaſure
    -1.32
     Chrift
    -1.28
     Diſ
    -1.28
    POSITIVE LOGITS
    m
    0.93
    k
    0.85
    r
    0.82
     to
    0.81
     so
    0.81
    d
    0.77
    n
    0.75
     as
    0.74
    ,
    0.73
    c
    0.71
    Activations Density 2.012%

    No Known Activations