© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7702
    Prev
    Next
    INDEX
    Explanations

    words related to physical action and body parts

    oai_token-act-pair · gemini-2.0-flash

    body part: arms/shoulders

    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
     “
    -0.54
     […]
    -0.50
     "
    -0.47
     co
    -0.45
    </i>
    -0.45
    eds
    -0.45
     «
    -0.44
    ../../
    -0.44
     country
    -0.44
    今朝
    -0.43
    POSITIVE LOGITS
    istoitu
    0.81
    bootstrapcdn
    0.76
     beginnetje
    0.76
    mybatisplus
    0.75
    AxisAlignment
    0.75
     himo
    0.75
     فريبيس
    0.72
     sportiva
    0.70
     getItemId
    0.69
     Athletes
    0.68
    Activations Density 1.567%

    No Known Activations