© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11469
    Prev
    Next
    INDEX
    Explanations

    words indicating someone giving testimony as part of a hearing or trial.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AndEndTag
    -0.60
     shocks
    -0.45
    stdc
    -0.43
    āya
    -0.42
    ruptedException
    -0.40
    бурга
    -0.40
    lgari
    -0.38
    phosa
    -0.38
    weile
    -0.37
     riguarda
    -0.36
    POSITIVE LOGITS
    ftagPool
    0.86
    SourceChecksum
    0.85
     للاسماء
    0.84
    IUrlHelper
    0.77
    DockStyle
    0.75
     وتسجيلات
    0.75
     estekak
    0.73
    errHandler
    0.73
    MigrationBuilder
    0.69
     jScrollPane
    0.68
    Activations Density 4.379%

    No Known Activations