© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142474
    Prev
    Next
    INDEX
    Explanations

    transplant, implant, plantillas

    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_0_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
    a
    2.63
    i
    2.28
    ه
    2.27
    k
    1.85
    د
    1.80
    in
    1.75
    o
    1.69
    น
    1.69
     and
    1.66
    an
    1.64
    POSITIVE LOGITS
    де
    1.52
    لي
    1.33
     entice
    1.30
    χρο
    1.30
    па
    1.29
    вели
    1.29
    ного
    1.28
     і
    1.26
    ної
    1.26
    он
    1.23
    Activations Density 0.001%

    No Known Activations