© 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. 45498
    Prev
    Next
    INDEX
    Explanations

    platonic, plasmonic

    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
     és
    0.82
    ing
    0.70
     представляет
    0.70
    ště
    0.69
     że
    0.67
     будет
    0.66
     предполагает
    0.66
    Ž
    0.66
     Ü
    0.65
     ಸ್ಟ
    0.65
    POSITIVE LOGITS
    in
    0.96
    يل
    0.80
    д
    0.68
     vVertex
    0.65
    mine
    0.63
    leg
    0.63
    iffany
    0.61
     років
    0.61
    ۔
    0.60
    inę
    0.59
    Activations Density 0.015%

    No Known Activations