© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    text or code in a non-English language(s) (possibly Croatian, Serbian, Portuguese, or Spanish) related to Facebook and coding-related terms

    oai_token-act-pair · gemini-2.0-flash

    links, foreign language, code

    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
     myſelf
    -1.27
     Eſ
    -1.19
     itſelf
    -1.18
     Efq
    -1.15
     greateſt
    -1.14
     Anſ
    -1.13
    出版年
    -1.13
     himſelf
    -1.13
     Theſe
    -1.09
     pleaſure
    -1.09
    POSITIVE LOGITS
     
    0.61
    ↵
    0.59
     Kon
    0.59
    <eos>
    0.59
      
    0.58
     kon
    0.57
     jak
    0.56
    ‘
    0.56
     –
    0.55
     je
    0.55
    Activations Density 0.143%

    No Known Activations