© 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. 123331
    Prev
    Next
    INDEX
    Explanations

    underappreciated / carriage / compact

    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
    จ
    0.82
    ש
    0.79
    지
    0.74
    ท์
    0.73
    nya
    0.73
    ย
    0.71
    ny
    0.69
    ้ง
    0.68
    স
    0.67
    سه
    0.67
    POSITIVE LOGITS
    r
    1.11
    a
    1.02
    c
    0.96
    ر
    0.95
    er
    0.95
    an
    0.80
    z
    0.79
    cathode
    0.76
    र
    0.75
    رین
    0.75
    Activations Density 0.001%

    No Known Activations