© 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. 41551
    Prev
    Next
    INDEX
    Explanations

    Phonics

    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
    。）
    0.68
    .
    0.66
    ิ
    0.65
    になる
    0.64
    ）：
    0.64
    ्रा
    0.62
    ۔
    0.62
     of
    0.62
    '
    0.61
    ции
    0.61
    POSITIVE LOGITS
    t
    0.79
    d
    0.74
    ש
    0.73
    dude
    0.73
    تالي
    0.71
    diği
    0.70
     montagna
    0.68
    la
    0.66
    lerini
    0.65
    le
    0.65
    Activations Density 0.001%

    No Known Activations