© 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. 158016
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ين
    1.27
    h
    0.99
    اد
    0.98
    ى
    0.95
    <0x99>
    0.93
    いを
    0.88
    ре
    0.86
    ше
    0.86
    もら
    0.86
    <0x93>
    0.84
    POSITIVE LOGITS
    行う
    1.09
    ON
    1.01
     I
    0.98
     to
    0.95
    த்தில்
    0.93
    TT
    0.93
    ка
    0.92
     for
    0.92
    ORD
    0.92
    CO
    0.91
    Activations Density 0.000%

    No Known Activations