© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141345
    Prev
    Next
    INDEX
    Explanations

    try

    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_46_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
    ုန်း
    0.39
    pid
    0.38
    guides
    0.37
     लैंग्वे
    0.37
     Throwable
    0.36
    ////
    0.36
     tongues
    0.36
    idh
    0.35
    }/{
    0.35
    centres
    0.35
    POSITIVE LOGITS
     catch
    0.82
     catches
    0.63
     Catch
    0.62
    Catch
    0.59
     catching
    0.56
    catch
    0.54
     catcher
    0.53
     блок
    0.47
     caught
    0.46
     block
    0.45
    Activations Density 0.002%

    No Known Activations