© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10697
    Prev
    Next
    INDEX
    Explanations

    legal and financial discussions, including dates, places, and organizations

    oai_token-act-pair · gemini-2.0-flash

    Business and formal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    
    -0.81
     дописавши
    -0.77
    twimg
    -0.76
    ValueStyle
    -0.73
     scolaires
    -0.71
     vectorielles
    -0.70
    ensement
    -0.69
     μὲν
    -0.68
    Autoritní
    -0.68
     estimés
    -0.65
    POSITIVE LOGITS
     Bour
    0.47
    oge
    0.47
    TRAILING
    0.47
    сня
    0.46
     Dur
    0.46
    ducted
    0.46
    alth
    0.45
     hy
    0.45
     west
    0.44
    jec
    0.44
    Activations Density 11.909%

    No Known Activations