© 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. 229364
    Prev
    Next
    INDEX
    Explanations

    Hed

    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
    ніза
    0.39
     Violation
    0.37
    ;++
    0.35
    olan
    0.35
    CCc
    0.35
     सीमेंट
    0.35
    之一
    0.35
    entin
    0.35
     खरीदना
    0.35
     zippered
    0.35
    POSITIVE LOGITS
    ude
    0.42
    bie
    0.41
    彝
    0.40
    bbe
    0.39
    ടാ
    0.39
    ukary
    0.39
    ுடைய
    0.38
     सकुशल
    0.38
    rue
    0.37
    ese
    0.37
    Activations Density 0.001%

    No Known Activations