© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37875
    Prev
    Next
    INDEX
    Explanations

    Vic

    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
     v
    0.46
     Us
    0.44
    tv
    0.44
     suv
    0.43
    Us
    0.43
    eu
    0.42
     VND
    0.42
    V
    0.41
    ei
    0.41
    ea
    0.41
    POSITIVE LOGITS
    uole
    0.52
    urist
    0.46
    ore
    0.45
    orene
    0.44
    uation
    0.44
    uting
    0.42
    ucch
    0.41
    uzione
    0.41
    메이션
    0.41
    ueness
    0.40
    Activations Density 0.006%

    No Known Activations