© 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. 8630
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal penalties, punishments, and crimes

    oai_token-act-pair · gemini-2.0-flash

    Fines and prison

    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
    providedIn
    -0.84
     CreateTagHelper
    -0.74
    ⓧ
    -0.72
    AutoScaleMode
    -0.67
    tvguidetime
    -0.66
     betweenstory
    -0.65
     يتيمه
    -0.63
     للاسماء
    -0.63
     AssemblyCulture
    -0.61
    OGND
    -0.57
    POSITIVE LOGITS
    Spoljašnje
    0.50
    Bibliographie
    0.50
    外部連結
    0.50
    Descripció
    0.48
    elu
    0.46
     useState
    0.46
    raciones
    0.45
    Спа
    0.45
     Спа
    0.44
    cina
    0.44
    Activations Density 1.576%

    No Known Activations