© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83932
    Prev
    Next
    INDEX
    Explanations

    Vuetify / Vuoi

    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_0_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
    ir
    2.14
    an
    2.13
    ar
    2.11
    n
    2.03
    a
    1.77
    al
    1.74
    z
    1.71
    ed
    1.69
    er
    1.66
    g
    1.62
    POSITIVE LOGITS
    大
    1.49
    Е
    1.38
    ש
    1.23
    pé
    1.13
    はず
    1.11
    は大
    1.10
     نهاية
    1.02
    此同时
    0.97
    К
    0.97
    nię
    0.96
    Activations Density 0.000%

    No Known Activations