© 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. 12185
    Prev
    Next
    INDEX
    Explanations

    text related to awards.

    oai_token-act-pair · gemini-2.0-flash

    story

    np_max-act · 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
    twimg
    -0.60
    enterOuterAlt
    -0.57
     الدولى
    -0.54
    Obrázky
    -0.53
    IBOutlet
    -0.53
     censiti
    -0.52
    :+:
    -0.52
     jotka
    -0.51
     Five
    -0.49
    setAccessible
    -0.49
    POSITIVE LOGITS
     Lk
    0.57
    teria
    0.56
    verted
    0.56
    DropTable
    0.56
    elemField
    0.54
     westfalen
    0.52
     picada
    0.52
    Xna
    0.51
    MetaType
    0.51
    >{"
    0.51
    Activations Density 3.114%

    No Known Activations