© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12438
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "his", "its", "the", "won", "seen", "found", "gain", "make", "figures", and/or "presence"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     متعلقه
    -0.82
    RectangleBorder
    -0.57
    Geplaatst
    -0.57
     Bastille
    -0.55
    DoubleQuotes
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    migrationBuilder
    -0.53
    StoryboardSegue
    -0.52
     propOrder
    -0.51
    +#+#
    -0.51
    POSITIVE LOGITS
    eech
    0.49
    itorious
    0.49
    IMATE
    0.48
    ivez
    0.48
    roux
    0.47
    itigen
    0.47
    azos
    0.47
    tys
    0.46
    zard
    0.46
    marken
    0.46
    Activations Density 0.662%

    No Known Activations