© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221249
    Prev
    Next
    INDEX
    Explanations

    sequence of items

    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_10_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
    し
    0.61
    ти
    0.56
    ាញ់
    0.51
    ﺍ
    0.47
     ثم
    0.46
     intimately
    0.45
     as
    0.45
    ৫
    0.45
     steril
    0.44
     rehearsals
    0.44
    POSITIVE LOGITS
    in
    0.54
    dbc
    0.46
    portál
    0.45
    łączy
    0.44
     Cities
    0.43
    akel
    0.42
    vič
    0.39
    ல்
    0.39
    lista
    0.39
    pertino
    0.39
    Activations Density 0.002%

    No Known Activations