© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34180
    Prev
    Next
    INDEX
    Explanations

    community generated

    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_7_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
    ab
    1.13
    را
    0.89
     be
    0.86
    е
    0.82
     can
    0.81
    im
    0.80
     =
    0.79
    ies
    0.77
    у
    0.77
     by
    0.76
    POSITIVE LOGITS
    t
    1.01
     rápidamente
    0.70
    dı
    0.68
    usuario
    0.68
    ,.
    0.67
    $('#
    0.67
     фонбет
    0.67
     والصلاه
    0.66
    ２
    0.66
    𝙛
    0.65
    Activations Density 0.095%

    No Known Activations