© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36644
    Prev
    Next
    INDEX
    Explanations

    expletives and intense words

    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_3_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
    3
    0.87
    2
    0.83
    ।
    0.80
    Dialog
    0.75
    4
    0.72
    I
    0.71
    。
    0.71
    1
    0.70
    ’
    0.70
    ↵↵
    0.70
    POSITIVE LOGITS
    し
    0.79
    нков
    0.67
     fearful
    0.66
     ficou
    0.66
     fleeing
    0.65
     painstakingly
    0.64
     prodotti
    0.64
     flocked
    0.64
    ﺶ
    0.63
     documentación
    0.63
    Activations Density 0.000%

    No Known Activations