© 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. 228880
    Prev
    Next
    INDEX
    Explanations

    주

    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
    ·
    0.38
     ·
    0.37
    ከር
    0.37
    ouveau
    0.35
     ani
    0.34
    ]`
    0.34
    福
    0.34
     τελευτα
    0.34
    `(
    0.34
    ത്മ
    0.34
    POSITIVE LOGITS
     Cullen
    0.39
     Grund
    0.38
    지가
    0.38
    amate
    0.37
    графи
    0.36
    attributes
    0.36
    approche
    0.36
     Barron
    0.35
     Pennington
    0.35
     gravity
    0.35
    Activations Density 0.000%

    No Known Activations