© 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. 13803
    Prev
    Next
    INDEX
    Explanations

    information about Formula 1 or Le Mans racing drivers, including their names, teams, and racing history

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'f' or 's' prefix

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

    having

    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
     itſelf
    -0.82
     myſelf
    -0.76
     poffible
    -0.74
     himſelf
    -0.73
     themſelves
    -0.72
     Eſ
    -0.72
     iſt
    -0.70
     Monfieur
    -0.69
     ſtand
    -0.69
     raiſ
    -0.69
    POSITIVE LOGITS
    <bos>
    0.61
     form
    0.57
     produce
    0.50
     s
    0.50
     sal
    0.48
     astore
    0.48
     con
    0.47
     f
    0.47
     av
    0.47
     am
    0.47
    Activations Density 0.517%

    No Known Activations