© 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. 58481
    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
    in
    1.30
    an
    1.27
     hundred
    1.27
    u
    1.27
    AN
    1.20
    er
    1.20
     January
    1.20
     February
    1.16
     have
    1.15
    ;
    1.14
    POSITIVE LOGITS
    ל
    1.74
    د
    1.55
    ри
    1.46
    ري
    1.34
    '
    1.34
    لا
    1.31
    يّ
    1.21
    本
    1.20
    هم
    1.17
    י
    1.17
    Activations Density 0.000%

    No Known Activations