© 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. 10607
    Prev
    Next
    INDEX
    Explanations

    content related to legal, tax, and financial services

    oai_token-act-pair · gemini-2.0-flash

    finances, construction, and DIY

    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
     Toten
    -0.51
     RULES
    -0.46
    textbackslash
    -0.45
    курс
    -0.45
    ={`
    -0.45
     Del
    -0.45
     vapor
    -0.44
    ampung
    -0.44
     Infórmanos
    -0.44
    czy
    -0.44
    POSITIVE LOGITS
     незавершена
    0.91
     NSCoder
    0.90
    UnusedPrivate
    0.80
    __':
    0.79
    __":
    0.78
    المناصب
    0.74
    fromnode
    0.73
    migrationBuilder
    0.71
     kaarangay
    0.69
    oa̍t
    0.69
    Activations Density 0.714%

    No Known Activations