© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140971
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    ون
    0.63
    لي
    0.60
    ica
    0.52
    Operation
    0.52
    M
    0.50
    يد
    0.50
    ow
    0.50
    Remove
    0.49
     movies
    0.49
    ון
    0.48
    POSITIVE LOGITS
    knings
    0.61
    谿
    0.60
    tis
    0.57
    ≐
    0.57
     wander
    0.56
    citation
    0.56
     delineation
    0.55
    t
    0.55
    できます
    0.54
     방정식
    0.54
    Activations Density 0.000%

    No Known Activations