© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6664
    Prev
    Next
    INDEX
    Explanations

    extremely sexually explicit descriptions of gay male sex, violent situations, and conditional statements.

    oai_token-act-pair · gemini-2.0-flash

    opinions/violent/sexual contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tvguidetime
    -0.74
    IGraphics
    -0.73
     noDo
    -0.70
    TintMode
    -0.69
    )");
    -0.68
     مرئيه
    -0.68
     endregion
    -0.66
    Билгалдахарш
    -0.66
     оригіналу
    -0.65
    脚注の使い方
    -0.63
    POSITIVE LOGITS
     who
    0.64
    openSession
    0.54
    Empty
    0.54
     empty
    0.47
     SCALE
    0.47
    who
    0.46
    asteroide
    0.46
     Char
    0.46
     scale
    0.46
     kelle
    0.45
    Activations Density 1.459%

    No Known Activations