© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11971
    Prev
    Next
    INDEX
    Explanations

    fitness levels

    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_13_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
     UP
    0.43
    铨
    0.40
     tarko
    0.40
     آئینے
    0.39
     لکھنے
    0.39
     UM
    0.38
     PINK
    0.38
     UPD
    0.38
     PAR
    0.37
     oxid
    0.37
    POSITIVE LOGITS
    (
    0.47
    an
    0.45
    ánicos
    0.42
    il
    0.41
    andus
    0.40
    ເຮ
    0.39
    in
    0.39
    trick
    0.39
    be
    0.38
    yta
    0.37
    Activations Density 0.003%

    No Known Activations