© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10748
    Prev
    Next
    INDEX
    Explanations

    words that indicate a helpful positive attitude

    oai_token-act-pair · gemini-2.0-flash

    Expressing opinions/questions

    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
    mybatisplus
    -0.85
    ArrowToggle
    -0.82
    brainly
    -0.77
     greateſt
    -0.77
     MainAxisSize
    -0.77
    XmlAccessType
    -0.74
    Kaynakça
    -0.74
    SuppressMessage
    -0.73
     SafeMath
    -0.73
     Conſ
    -0.71
    POSITIVE LOGITS
    </thead>
    0.46
     düş
    0.46
     {?>
    0.42
    se
    0.42
    ョ
    0.41
    ule
    0.41
     next
    0.40
    ستی
    0.40
    vas
    0.40
    ண
    0.40
    Activations Density 1.888%

    No Known Activations