© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112924
    Prev
    Next
    INDEX
    Explanations

    nitty-gritty

    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_2_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
    <0x80>
    1.48
    de
    1.20
    ra
    1.00
    س
    0.99
    ate
    0.98
    ت
    0.94
    S
    0.92
    A
    0.91
     of
    0.90
    I
    0.88
    POSITIVE LOGITS
    in
    1.27
     União
    1.02
    的名字
    0.97
    inę
    0.95
    ના
    0.94
    的安全
    0.94
    čnom
    0.93
     atteint
    0.93
     dupa
    0.92
    UD
    0.90
    Activations Density 0.000%

    No Known Activations