© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51408
    Prev
    Next
    INDEX
    Explanations

    plain text body

    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_31_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
     Evergreen
    0.38
     Sylvester
    0.38
    Ñ
    0.37
    NI
    0.37
     لاز
    0.37
     Docker
    0.36
    Infrastructure
    0.36
     Plan
    0.36
     Ceres
    0.36
     Ñ
    0.35
    POSITIVE LOGITS
     contentLength
    0.49
     encouraging
    0.45
    ATTACH
    0.41
     Attach
    0.41
     kawa
    0.41
    quins
    0.40
     applaud
    0.39
     apologizing
    0.39
    elsch
    0.39
     appla
    0.38
    Activations Density 0.001%

    No Known Activations