© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45384
    Prev
    Next
    INDEX
    Explanations

    profanity and strong language

    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_13_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
    u
    0.47
    ستي
    0.46
    i
    0.46
    ي
    0.45
    er
    0.44
    இ
    0.43
    ഇ
    0.43
     jeopard
    0.42
     preko
    0.42
    id
    0.42
    POSITIVE LOGITS
    </code>
    0.52
     사
    0.46
     ตุลาคม
    0.45
     손
    0.42
    вана
    0.42
     кандай
    0.42
     січня
    0.42
     감소
    0.41
     верхней
    0.41
     상
    0.40
    Activations Density 0.006%

    No Known Activations