© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12653
    Prev
    Next
    INDEX
    Explanations

    a diverse set of words related to problem-solving, teamwork, and goals.

    oai_token-act-pair · gemini-2.0-flash

    sort

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MigrationBuilder
    -0.65
     gyhoeddwyd
    -0.54
     ModelExpression
    -0.47
     rire
    -0.46
    τουργ
    -0.45
     Paso
    -0.45
     Nog
    -0.45
    المكان
    -0.43
    Demografía
    -0.42
    >{@
    -0.41
    POSITIVE LOGITS
     sort
    3.34
     sorts
    2.72
    sort
    2.69
     Sort
    2.53
    Sort
    2.25
     SORT
    2.14
    SORT
    1.76
     sorta
    1.76
     sorte
    1.36
     sortBy
    1.29
    Activations Density 11.949%

    No Known Activations