© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88610
    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_23_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
    cc
    0.39
    ']=
    0.38
     git
    0.38
    ((
    0.37
     הוא
    0.36
    ]=
    0.34
     surrounded
    0.34
     coloc
    0.34
    AL
    0.34
     '.
    0.34
    POSITIVE LOGITS
     aplikace
    0.52
    identical
    0.49
    휙
    0.48
    디오
    0.43
    skou
    0.42
     identiques
    0.42
    𒃶
    0.42
     identique
    0.42
    ♊
    0.41
     curviliné
    0.41
    Activations Density 0.000%

    No Known Activations