© 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. 2102
    Prev
    Next
    INDEX
    Explanations

    words related to people and events at a party

    oai_token-act-pair · gemini-2.0-flash

    names or irrelevant jargon

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

    Real-life events

    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
    ValueStyle
    -0.53
    modelBuilder
    -0.47
    ibatis
    -0.47
    scrapy
    -0.45
    ://$
    -0.43
    errHandler
    -0.42
    DataColumn
    -0.42
     evenement
    -0.41
     kuiten
    -0.41
    SPJ
    -0.41
    POSITIVE LOGITS
    Viited
    0.71
    hetics
    0.67
    LookAnd
    0.66
     المعيارى
    0.65
    FTFY
    0.60
     CURLOPT
    0.59
    hability
    0.59
    rungsseite
    0.59
     Ide
    0.59
    ///</
    0.58
    Activations Density 2.787%

    No Known Activations