© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61810
    Prev
    Next
    INDEX
    Explanations

    Rate, Bonds, Classes, Participation

    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_11_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
    well
    0.43
    tuning
    0.40
    simplex
    0.38
    t
    0.38
    ties
    0.38
    better
    0.37
    simple
    0.37
    കൊ
    0.37
    work
    0.36
    به
    0.36
    POSITIVE LOGITS
     Πα
    0.36
     jeopardize
    0.36
     ಮೇ
    0.34
    ]%
    0.34
     %),
    0.34
     για
    0.33
     POINTS
    0.33
     Кам
    0.33
    iritual
    0.32
     Mn
    0.32
    Activations Density 0.010%

    No Known Activations