© 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. 10557
    Prev
    Next
    INDEX
    Explanations

    mentions of measuring devices and tools, but also seems to activate on the word "collect" and the concept of selling

    oai_token-act-pair · gemini-2.0-flash

    instrument

    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
    rrggbb
    -1.00
     Мексичка
    -0.81
     endwhile
    -0.77
    readAs
    -0.69
    ThroughAttribute
    -0.69
    troppo
    -0.69
    تقاوى
    -0.68
    endwhile
    -0.68
    скажите
    -0.67
    hObject
    -0.66
    POSITIVE LOGITS
    ी
    0.58
     Obispo
    0.55
    usermodel
    0.54
     wrench
    0.54
     الاطلاع
    0.53
     phones
    0.53
     moths
    0.53
     Itali
    0.53
    il
    0.52
     frit
    0.52
    Activations Density 1.162%

    No Known Activations