© 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-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3025
    Prev
    Next
    INDEX
    Explanations

    harmful unethical content refusal

    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_39_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
     disliked
    0.45
     불편
    0.41
    Congrats
    0.40
    恭
    0.40
    }}=-\
    0.39
     `:`,
    0.39
     cautionary
    0.38
    ^{*}=\
    0.37
     شلون
    0.37
    祝福
    0.37
    POSITIVE LOGITS
    portions
    0.38
     plain
    0.38
    onyms
    0.38
    ischem
    0.37
     Plain
    0.36
     portions
    0.36
    olius
    0.35
     Mr
    0.35
     Stro
    0.34
     verbatim
    0.34
    Activations Density 0.158%

    No Known Activations