© 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. 130158
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    fen
    0.39
    stellt
    0.36
    우
    0.36
    ē
    0.36
    ະ
    0.36
    फिट
    0.36
    odec
    0.35
    ceans
    0.35
    砀
    0.35
     überras
    0.34
    POSITIVE LOGITS
     direct
    0.42
     generally
    0.39
    рити
    0.39
     both
    0.38
     Sequential
    0.38
     bonded
    0.37
     changeable
    0.37
     conversion
    0.37
     which
    0.37
    חת
    0.36
    Activations Density 0.005%

    No Known Activations