© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25756
    Prev
    Next
    INDEX
    Explanations

    leading zeros

    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_10_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
     of
    0.93
    {
    0.88
    $
    0.86
    \
    0.84
     on
    0.79
     twee
    0.76
    :“
    0.76
     piloted
    0.75
     tanned
    0.74
     तरह
    0.71
    POSITIVE LOGITS
    S
    1.12
    F
    1.04
    y
    0.99
    P
    0.96
    R
    0.94
    n
    0.93
    و
    0.93
    o
    0.90
    L
    0.88
    ع
    0.87
    Activations Density 0.013%

    No Known Activations