© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237085
    Prev
    Next
    INDEX
    Explanations

    is a/an

    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_32_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
    幵
    0.47
    䀖
    0.44
     धक्का
    0.41
    ถ
    0.41
     উদাহরণ
    0.38
    কার
    0.38
    结合
    0.38
    昦
    0.38
    ปร
    0.37
    䢁
    0.36
    POSITIVE LOGITS
     thrives
    0.40
     chow
    0.39
    kb
    0.37
    yx
    0.36
     mozzarella
    0.36
     tla
    0.36
     logic
    0.35
     causa
    0.35
     waits
    0.35
     nig
    0.35
    Activations Density 0.001%

    No Known Activations