© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121615
    Prev
    Next
    INDEX
    Explanations

    profanity and swearing

    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_38_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
     slang
    0.53
    las
    0.42
     Revol
    0.40
    ivu
    0.39
    wski
    0.38
    涛
    0.38
    Language
    0.37
    ву
    0.37
    Vul
    0.37
    JM
    0.37
    POSITIVE LOGITS
    Ἱ
    0.40
     WEIGHT
    0.40
     軽量
    0.38
     frustrate
    0.38
    購
    0.37
    Ἠ
    0.37
    permissionid
    0.37
     veterin
    0.37
     medicamentos
    0.37
     Arzneim
    0.37
    Activations Density 0.012%

    No Known Activations