© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16402
    Prev
    Next
    INDEX
    Explanations

    Mär

    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_15_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
    ف
    0.46
    שא
    0.45
    رو
    0.45
    Condition
    0.43
    ضم
    0.43
    Been
    0.42
    ALLOW
    0.42
    م
    0.42
    די
    0.41
    স
    0.41
    POSITIVE LOGITS
     රා
    0.54
     n
    0.52
     dreamed
    0.52
     specialised
    0.52
     rêve
    0.51
     новой
    0.50
     ශ
    0.50
     NumericVector
    0.49
     Hyg
    0.49
     dreamt
    0.47
    Activations Density 0.001%

    No Known Activations