© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141762
    Prev
    Next
    INDEX
    Explanations

    condor, panther, or cond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    ć
    0.55
     beetles
    0.46
     racket
    0.46
     matchups
    0.46
     abhor
    0.46
     provocative
    0.45
     credible
    0.45
     demonstra
    0.45
     codef
    0.45
     مسئول
    0.45
    POSITIVE LOGITS
    الص
    0.58
    Forest
    0.52
    Transport
    0.51
    лизации
    0.50
    ار
    0.49
    መ
    0.48
    Conversation
    0.48
    Collapsed
    0.47
    初期
    0.47
    بول
    0.47
    Activations Density 0.000%

    No Known Activations