© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10277
    Prev
    Next
    INDEX
    Explanations

    coverglass, resin, molding, safety

    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_13_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
    dirt
    0.48
    1
    0.48
    5
    0.47
    change
    0.47
    </strong>
    0.46
    f
    0.45
    dit
    0.43
    reg
    0.43
    Dirt
    0.43
    but
    0.43
    POSITIVE LOGITS
     समस्त
    0.46
     peaks
    0.42
     économ
    0.41
     pyramidal
    0.41
     quartiers
    0.41
     😊
    0.41
     vertex
    0.40
     фестива
    0.39
    glRaster
    0.39
    lü
    0.39
    Activations Density 0.010%

    No Known Activations