© 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. 77944
    Prev
    Next
    INDEX
    Explanations

    list length prefixes

    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
     menyebabkan
    0.35
     powod
    0.35
     mancanza
    0.35
     spowod
    0.33
    muz
    0.33
    woorden
    0.32
    靈
    0.32
     conclud
    0.32
    jegyz
    0.32
    foundland
    0.32
    POSITIVE LOGITS
     быстрее
    0.39
     immature
    0.36
     شائع
    0.36
    সংস্কার
    0.36
     templates
    0.34
     Smaller
    0.34
    垃
    0.34
     осень
    0.33
    彼此
    0.32
     IAM
    0.32
    Activations Density 0.002%

    No Known Activations