© 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. 80675
    Prev
    Next
    INDEX
    Explanations

    refusal, explanation, harm, ethical violation

    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
    :
    0.60
    ार्थियों
    0.39
    Oscar
    0.38
     :
    0.38
    ():
    0.38
    াকের
    0.38
    ：
    0.37
    Zawodnik
    0.37
     обла
    0.36
    ઃ
    0.36
    POSITIVE LOGITS
    âm
    0.38
    vrage
    0.36
     verhindern
    0.35
     świe
    0.34
    🚱
    0.34
     준비
    0.34
    printStackTrace
    0.33
    啶
    0.33
    excludeFolder
    0.33
     parametros
    0.33
    Activations Density 0.032%

    No Known Activations