© 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. 7722
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and related words expressing personal thoughts and opinions

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords and phrases

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

    I

    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
    aniline
    -0.52
    addPreferredGap
    -0.50
    vol
    -0.50
    didSet
    -0.48
    bigskip
    -0.47
    splitlines
    -0.46
     Setup
    -0.45
    CreateModel
    -0.44
     Assignee
    -0.44
    役
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.65
    migrationBuilder
    0.65
    ^(@)
    0.57
    Obrigada
    0.56
    ArgumentParser
    0.55
    afficheront
    0.55
    FieldBuilder
    0.55
     صوتيه
    0.54
     кӀош
    0.54
    UseVisualStyle
    0.54
    Activations Density 0.664%

    No Known Activations