© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59036
    Prev
    Next
    INDEX
    Explanations

    Old

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    린
    0.44
     многи
    0.43
    лан
    0.40
    ريك
    0.39
     डीएस
    0.39
     DSC
    0.38
    ере
    0.38
    girl
    0.38
    橡
    0.38
    renn
    0.38
    POSITIVE LOGITS
     Old
    0.68
    Old
    0.68
    little
    0.49
     little
    0.46
    Little
    0.45
     too
    0.42
     OLD
    0.40
    OLD
    0.39
    King
    0.39
     ம
    0.38
    Activations Density 0.002%

    No Known Activations