© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43069
    Prev
    Next
    INDEX
    Explanations

    Slovenia, Slovak, SLP parsing

    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
    ן
    0.78
    dokument
    0.74
    ur
    0.71
     쓰고
    0.69
    f
    0.69
    nél
    0.67
    सी
    0.66
    k
    0.65
    ير
    0.65
    x
    0.63
    POSITIVE LOGITS
    л
    0.82
     regreso
    0.76
    ل
    0.75
     llevado
    0.71
     precisión
    0.70
    ों
    0.68
     готовы
    0.67
    í
    0.66
    いろいろ
    0.66
    It
    0.64
    Activations Density 0.009%

    No Known Activations