© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 245
    Prev
    Next
    INDEX
    Explanations

    words related to hobbies and crafts like sewing, playing, and dancing, plus casual conversational punctuation

    oai_token-act-pair · gemini-2.0-flash

    hobbies/activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     démocr
    -0.88
     citoy
    -0.80
     épaules
    -0.79
    Obrázky
    -0.77
     NDEBUG
    -0.73
     chré
    -0.73
     traités
    -0.72
     sociaux
    -0.72
     Diretto
    -0.72
     Efq
    -0.71
    POSITIVE LOGITS
     til
    0.47
    ншни
    0.43
     at
    0.41
     primas
    0.41
    Reviewed
    0.41
     ra
    0.41
    ണം
    0.41
     հղումներ
    0.40
    Having
    0.39
    MigrationBuilder
    0.39
    Activations Density 12.887%

    No Known Activations