© 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. 42358
    Prev
    Next
    INDEX
    Explanations

    config files `.php`, `.yml`, `.txt`

    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
    g
    0.98
    d
    0.94
    k
    0.86
    t
    0.79
    i
    0.71
    l
    0.70
    c
    0.68
    a
    0.67
    grav
    0.67
    p
    0.67
    POSITIVE LOGITS
    ر
    0.86
     on
    0.74
    ButtonClick
    0.66
    กว่า
    0.66
    ม
    0.64
    ク
    0.63
    มอง
    0.61
    ы
    0.61
    رک
    0.61
    ς
    0.61
    Activations Density 0.005%

    No Known Activations