© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10710
    Prev
    Next
    INDEX
    Explanations

    structured data

    oai_token-act-pair · gemini-2.0-flash

    terms related to 'double' or 'duality'

    np_token-act-pair-logits · gpt-4o-mini

    technical/scientific language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Thursday
    -0.66
     Thursdays
    -0.64
    mbu
    -0.64
     thursday
    -0.62
    وعة
    -0.56
    Thursday
    -0.54
     Wednesday
    -0.54
    
    -0.53
     Wednesdays
    -0.53
     fourteenth
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
     double
    0.68
     AspNetCore
    0.66
    doub
    0.63
     dual
    0.61
    WebControls
    0.61
     doppio
    0.61
    ②
    0.60
    double
    0.58
    Doppel
    0.58
    Activations Density 2.098%

    No Known Activations