© 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. 9338
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and formulas

    oai_token-act-pair · gemini-2.0-flash

    terms related to partial differentiation

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

    partial

    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
    IBOutlet
    -0.56
    DispatchToProps
    -0.52
    NamedQueries
    -0.49
     unknownFields
    -0.46
     ModelExpression
    -0.46
    новниш
    -0.45
     feeders
    -0.45
    AntiForgeryToken
    -0.44
     Cataloging
    -0.44
    Espèce
    -0.44
    POSITIVE LOGITS
     partial
    0.99
    Partial
    0.86
     partially
    0.85
     Partial
    0.84
     Partially
    0.75
    Parti
    0.72
     parcial
    0.72
    partial
    0.66
    parti
    0.65
     partly
    0.64
    Activations Density 2.689%

    No Known Activations