© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127616
    Prev
    Next
    INDEX
    Explanations

    adult male

    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
    0
    0.61
    ，
    0.60
    다는
    0.59
    ل
    0.58
     as
    0.56
    ،
    0.56
    }}.
    0.54
    }.
    0.53
    ה
    0.52
     by
    0.52
    POSITIVE LOGITS
     umowy
    0.69
     marihuana
    0.58
    させて頂
    0.58
     terrem
    0.57
     защиты
    0.55
    ي
    0.55
     jugadores
    0.54
     وك
    0.54
     sinar
    0.54
     सभी
    0.53
    Activations Density 0.003%

    No Known Activations