© 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. 153681
    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
     నిర్మా
    0.43
    icier
    0.42
    '];
    0.41
    StructOf
    0.40
    MktCap
    0.40
    ٢
    0.39
    Gum
    0.39
     పాట
    0.38
    <unused28>
    0.38
    laşı
    0.38
    POSITIVE LOGITS
    ောင့်
    0.44
     violencia
    0.43
     occupant
    0.41
    කි
    0.41
    Université
    0.40
     humanoid
    0.40
     ठा
    0.40
     coerce
    0.40
     triang
    0.39
     vulgaris
    0.39
    Activations Density 0.000%

    No Known Activations