© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130576
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    优点
    0.38
     Arran
    0.38
     ازاي
    0.38
     Masai
    0.37
     Com
    0.37
    </h3>
    0.36
     Disneyland
    0.36
     Para
    0.35
     INSTIT
    0.35
     (
    0.35
    POSITIVE LOGITS
     quadrant
    0.44
    ourced
    0.41
    iter
    0.39
     constituent
    0.39
     customary
    0.39
    oxidation
    0.39
     wider
    0.39
     groundwater
    0.38
    wider
    0.38
    panel
    0.38
    Activations Density 0.000%

    No Known Activations