© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39387
    Prev
    Next
    INDEX
    Explanations

    Crit

    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
     카
    0.87
     ка
    0.86
    カ
    0.85
    카
    0.79
     κα
    0.66
     kam
    0.65
     Κα
    0.65
     Kam
    0.64
    Ka
    0.63
     Ка
    0.62
    POSITIVE LOGITS
    C
    2.00
     C
    1.75
    c
    1.58
     c
    1.55
    setC
    1.32
     ค
    1.20
    <0x83>
    1.16
     الص
    1.13
     ص
    1.05
    ค
    1.02
    Activations Density 0.004%

    No Known Activations