© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7018
    Prev
    Next
    INDEX
    Explanations

    avoiding sounding inappropriate

    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
    装饰
    0.38
     Decorative
    0.38
    汎
    0.37
     barbaric
    0.37
     dangerous
    0.37
    ंपरा
    0.36
     speculate
    0.36
    篡
    0.36
     Gorgeous
    0.35
    温柔
    0.35
    POSITIVE LOGITS
     disappointed
    0.41
    恥
    0.41
     embarrassed
    0.40
     turn
    0.40
    尷
    0.39
     dated
    0.39
    cling
    0.39
     Embar
    0.39
     cliche
    0.39
     flop
    0.38
    Activations Density 0.126%

    No Known Activations