© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21812
    Prev
    Next
    INDEX
    Explanations

    men

    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
     grow
    0.81
     Grow
    0.67
    grow
    0.66
    Grow
    0.54
    男
    0.46
    nu
    0.41
     मधुर
    0.40
     Male
    0.39
     GROW
    0.39
     男
    0.39
    POSITIVE LOGITS
     adult
    1.66
     Adult
    1.53
    ผู้
    1.48
     ผู้
    1.18
    adult
    1.12
    Adult
    1.07
    成人
    1.07
    ของผู้
    1.02
     adolescent
    0.95
    ຜູ້
    0.95
    Activations Density 0.096%

    No Known Activations