© 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. 176709
    Prev
    Next
    INDEX
    Explanations

    Georgian places

    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
    wach
    0.44
     voucher
    0.42
     Chakraborty
    0.42
    汪
    0.41
     Bé
    0.41
    iados
    0.39
    vori
    0.39
    Gab
    0.38
     వ
    0.38
    ania
    0.38
    POSITIVE LOGITS
    кле
    0.42
    สำเร็จ
    0.40
    لع
    0.39
    uffles
    0.39
    TK
    0.38
    ತೆ
    0.38
    OLOGICAL
    0.38
    쿄
    0.38
    iggle
    0.37
    etes
    0.37
    Activations Density 0.000%

    No Known Activations