© 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. 157438
    Prev
    Next
    INDEX
    Explanations

    Aimybox, pointy hat, Neal Stephenson

    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
    ের
    1.37
    та
    1.31
    ਾ
    1.19
    é
    1.11
    {
    1.09
    т
    1.08
    માં
    1.05
    મ
    1.05
    ف
    1.01
    দের
    0.99
    POSITIVE LOGITS
    I
    0.97
     that
    0.94
    a
    0.82
     이미
    0.82
     $\
    0.79
    NZ
    0.78
    maßen
    0.78
    bread
    0.77
    ies
    0.76
    าน
    0.76
    Activations Density 0.000%

    No Known Activations