© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48831
    Prev
    Next
    INDEX
    Explanations

    sexually explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    微生物
    0.31
    वसु
    0.31
    ෲ
    0.29
     dodat
    0.28
    शेष
    0.28
    زش
    0.27
     LOS
    0.27
    クリーム
    0.27
    液体
    0.27
    heets
    0.27
    POSITIVE LOGITS
    collation
    0.31
    Crist
    0.31
    Sprintf
    0.31
    atakse
    0.30
    aschen
    0.30
    ஞ
    0.30
    loir
    0.30
    ǎn
    0.30
     Skies
    0.30
    Sp
    0.29
    Activations Density 0.257%

    No Known Activations