© 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. 46868
    Prev
    Next
    INDEX
    Explanations

    union square, army

    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
    a
    1.18
    i
    0.93
    f
    0.93
    ي
    0.89
    kör
    0.77
    b
    0.74
    j
    0.73
    া
    0.68
    k
    0.68
    vollen
    0.67
    POSITIVE LOGITS
    (
    0.98
    ี่
    0.70
    ate
    0.70
    ید
    0.68
    มีการ
    0.58
    ation
    0.57
    ка
    0.57
    0.57
    ดี
    0.56
    ูก
    0.55
    Activations Density 0.001%

    No Known Activations