© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108798
    Prev
    Next
    INDEX
    Explanations

    slicer

    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_2_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
    การ
    1.76
    는
    1.61
    ع
    1.45
    是
    1.40
    />
    1.26
    를
    1.23
    ت
    1.19
    v
    1.13
    ك
    1.13
    ق
    1.12
    POSITIVE LOGITS
    ني
    1.04
     dirigeants
    1.01
     welke
    1.00
     aanwezig
    0.99
     بيان
    0.98
     لي
    0.94
     welchen
    0.94
     terug
    0.93
     není
    0.93
     begle
    0.93
    Activations Density 0.000%

    No Known Activations