© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32829
    Prev
    Next
    INDEX
    Explanations

    say "keit" ending

    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_50_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
     Sch
    0.93
    sch
    0.69
    Sch
    0.66
     sch
    0.62
     الش
    0.57
     Ш
    0.55
     scherm
    0.45
     Schur
    0.45
     schizophrenia
    0.44
     Ş
    0.44
    POSITIVE LOGITS
    keit
    0.96
    ike
    0.82
    KE
    0.77
     ke
    0.73
    ке
    0.73
    케
    0.72
    keits
    0.72
    keiten
    0.71
    เค
    0.71
    kei
    0.71
    Activations Density 0.002%

    No Known Activations