© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3156
    Prev
    Next
    INDEX
    Explanations

    references to the NASCAR racing series

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

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

    NASCAR

    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
    makeatother
    -0.43
     /\.
    -0.43
     fermo
    -0.41
    onedDateTime
    -0.41
    ComponentScan
    -0.40
     Fundamental
    -0.40
    smiley
    -0.39
    iam
    -0.38
    argmin
    -0.37
    distributed
    -0.37
    POSITIVE LOGITS
    divia
    0.67
     SqlDbType
    0.66
     "..\..\
    0.63
     "..\..\..\
    0.63
    rungsseite
    0.62
    坞
    0.62
    IndentedString
    0.61
     lenker
    0.61
     незавершена
    0.59
    legel
    0.59
    Activations Density 0.650%

    No Known Activations