© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34721
    Prev
    Next
    INDEX
    Explanations

    Material UI (MUI)

    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_3_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
    Material
    0.82
    V
    0.73
    M
    0.72
    H
    0.72
    J
    0.70
     been
    0.69
    Muse
    0.68
     be
    0.67
    K
    0.66
    F
    0.65
    POSITIVE LOGITS
     simpat
    0.63
    ین
    0.58
     uplifting
    0.57
    un
    0.57
     interni
    0.57
     inscr
    0.57
    لم
    0.55
    ingos
    0.54
    𝗹
    0.54
     synthes
    0.53
    Activations Density 0.002%

    No Known Activations