© 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. 2753
    Prev
    Next
    INDEX
    Explanations

    equations and mathematical symbols.

    oai_token-act-pair · gemini-2.0-flash

    mathematical symbols and variables

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

    mathematical formulas and equations

    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
     Numerade
    -0.55
    новниш
    -0.52
    GTCX
    -0.49
     plezier
    -0.49
    Affirmed
    -0.49
    PreferredItem
    -0.49
    ็จ
    -0.49
     bobina
    -0.48
    السكان
    -0.48
     getCount
    -0.47
    POSITIVE LOGITS
     insuffisamment
    0.73
    saraba
    0.58
    StoryboardSegue
    0.56
    #![
    0.56
     متعلقه
    0.55
    ⓧ
    0.55
    galo
    0.52
    *
    0.50
    Vía
    0.50
     saites
    0.49
    Activations Density 3.788%

    No Known Activations