© 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. 8852
    Prev
    Next
    INDEX
    Explanations

    words and phrases dealing with prevalence or patterns

    oai_token-act-pair · gemini-2.0-flash

    common

    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
     vun
    -0.50
    indakan
    -0.48
    bility
    -0.48
    ieh
    -0.47
     cellspacing
    -0.47
     Offen
    -0.47
     regency
    -0.46
    ષ
    -0.46
     Spin
    -0.45
     clicks
    -0.45
    POSITIVE LOGITS
    __*/
    0.70
    IntoConstraints
    0.68
    createCanvas
    0.64
    InitVars
    0.63
    MLLoader
    0.63
    meist
    0.63
    =");
    0.62
     htons
    0.60
    "");
    0.60
     '\\;'
    0.60
    Activations Density 0.566%

    No Known Activations