© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199508
    Prev
    Next
    INDEX
    Explanations

    multilingual word fragments

    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
    uniya
    0.43
    ņa
    0.42
    Dar
    0.41
    upani
    0.40
    ક્સ
    0.39
    목
    0.39
    ONY
    0.38
    onya
    0.38
     Ast
    0.38
     Дан
    0.38
    POSITIVE LOGITS
     ترا
    0.42
    itzer
    0.41
    anco
    0.38
    ﾋ
    0.38
     Bisc
    0.38
     teg
    0.36
     نط
    0.36
    કર્
    0.36
    icom
    0.36
     नकल
    0.36
    Activations Density 0.000%

    No Known Activations