© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15680
    Prev
    Next
    INDEX
    Explanations

    Chiang Mai, pacman

    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_34_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
     जिंद
    0.44
     transformar
    0.42
     সমিত
    0.41
    转换
    0.40
    &&\
    0.39
     speedboat
    0.39
    ക്ത
    0.39
     champagne
    0.39
     Hussein
    0.39
    Pierce
    0.38
    POSITIVE LOGITS
     මි
    0.42
     Tucson
    0.37
    狸
    0.36
    ARIFF
    0.36
     lol
    0.35
     ARI
    0.35
    溽
    0.34
     Enlight
    0.34
     owning
    0.34
     Lol
    0.33
    Activations Density 0.012%

    No Known Activations