© 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. 58689
    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
    al
    1.45
    in
    1.43
    ar
    1.34
    ن
    1.34
    on
    1.30
    an
    1.27
    น
    1.24
     powied
    1.23
    as
    1.21
    t
    1.19
    POSITIVE LOGITS
    ۰
    1.42
     You
    1.13
     It
    1.12
    ני
    1.03
    ך
    0.98
     OBD
    0.97
     cardiologist
    0.97
     ASAP
    0.97
    ০০
    0.95
    며
    0.95
    Activations Density 0.000%

    No Known Activations