© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170267
    Prev
    Next
    INDEX
    Explanations

    Text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     V
    1.28
    V
    0.95
    Dom
    0.77
     Dom
    0.76
    Ｖ
    0.69
     dom
    0.62
    dom
    0.61
    Ⅴ
    0.58
    𝐕
    0.58
    𝑉
    0.54
    POSITIVE LOGITS
     sexual
    1.06
     Sexual
    0.91
    Sexual
    0.91
    sexual
    0.87
     यौन
    0.79
     SEXUAL
    0.78
     seksual
    0.77
     sexuales
    0.75
     sexuality
    0.70
     seks
    0.68
    Activations Density 0.003%

    No Known Activations