© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62835
    Prev
    Next
    INDEX
    Explanations

    logging configuration level

    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_41_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
     environments
    0.49
     ambientes
    0.48
     ambienti
    0.48
    environments
    0.46
    环境中
    0.46
     Environments
    0.45
    ermes
    0.43
    秾
    0.43
     logics
    0.40
     двор
    0.39
    POSITIVE LOGITS
     meeting
    0.35
    rev
    0.35
     module
    0.34
    assem
    0.34
    сик
    0.33
    vou
    0.33
    ネタ
    0.33
    훗
    0.33
    WK
    0.32
    sss
    0.32
    Activations Density 0.000%

    No Known Activations