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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130486
    Prev
    Next
    INDEX
    Explanations

    stock tickers and abbreviations

    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_25_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
    аб
    0.42
     जावेद
    0.41
     affirmations
    0.41
     nummer
    0.40
     פ
    0.40
    ੰਜ
    0.40
     tilts
    0.40
     図
    0.39
     এমনকি
    0.39
     لكن
    0.39
    POSITIVE LOGITS
     Haiti
    0.44
    人在
    0.40
     Parlamento
    0.39
     Vantage
    0.39
     Dominion
    0.38
     Schw
    0.37
     Schl
    0.37
     prover
    0.37
     Hempstead
    0.37
     WWII
    0.37
    Activations Density 0.001%

    No Known Activations