© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229326
    Prev
    Next
    INDEX
    Explanations

    say business entities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ことがあります
    0.43
    望
    0.37
     fac
    0.35
     Billion
    0.35
     вос
    0.34
    প্রশ
    0.34
     тик
    0.34
    晝
    0.33
    chainId
    0.33
     Kipp
    0.33
    POSITIVE LOGITS
     holding
    1.88
    Holding
    1.61
    holding
    1.55
     Holding
    1.53
     концер
    1.24
     concern
    1.20
     holdings
    1.13
    concern
    1.12
     hold
    1.05
     Concern
    1.03
    Activations Density 0.020%

    No Known Activations