© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13976
    Prev
    Next
    INDEX
    Explanations

    the character '['

    oai_token-act-pair · gemini-2.0-flash

    code, data structures

    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
    <h1>
    -0.38
    PRNewswire
    -0.37
    ————————————————
    -0.34
    ]='\
    -0.34
    )|^{
    -0.33
    ogue
    -0.33
    Many
    -0.33
    redacted
    -0.33
     ",";
    -0.31
    artz
    -0.31
    POSITIVE LOGITS
    enumi
    0.82
     समीक्षक
    0.78
    الإنجليزية
    0.71
    tagHelperRunner
    0.71
    Personensuche
    0.70
    SceneManagement
    0.69
    bootstrapcdn
    0.69
     Normdatei
    0.68
    новниш
    0.64
    LookAnd
    0.64
    Activations Density 0.841%

    No Known Activations