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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13152
    Prev
    Next
    INDEX
    Explanations

    words related to the physical human body

    oai_token-act-pair · gemini-2.0-flash

    body/pain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    astify
    -0.71
    moveToFirst
    -0.60
     चीज़ों
    -0.59
    awaiter
    -0.59
    ArgsConstructor
    -0.57
    /*++
    -0.57
    ordnet
    -0.56
     Вікі
    -0.55
     eyelashes
    -0.55
    ScopeManager
    -0.55
    POSITIVE LOGITS
     body
    1.16
     Body
    1.08
     bodies
    1.00
     BODY
    0.93
    Body
    0.91
    body
    0.88
     Bodies
    0.87
     Körper
    0.82
    ボディ
    0.79
     bodys
    0.78
    Activations Density 1.256%

    No Known Activations