© 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. 34868
    Prev
    Next
    INDEX
    Explanations

    showdown or image origin

    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
    ↵
    0.97
    ל
    0.86
    ется
    0.85
    ش
    0.81
    ก
    0.77
    ри
    0.71
    گ
    0.70
    ل
    0.68
    ات
    0.68
    ल
    0.68
    POSITIVE LOGITS
    a
    1.22
    on
    0.87
    u
    0.75
    f
    0.75
    in
    0.72
     yıll
    0.71
    worth
    0.66
    r
    0.66
    া
    0.65
    at
    0.64
    Activations Density 0.008%

    No Known Activations