© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39251
    Prev
    Next
    INDEX
    Explanations

    Italian word parts

    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_57_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
    zi
    0.54
    si
    0.50
    scor
    0.48
    zata
    0.46
    зай
    0.46
    sig
    0.45
    zo
    0.45
    ସ
    0.44
    سی
    0.43
    za
    0.43
    POSITIVE LOGITS
    uito
    0.50
    utto
    0.37
    oggler
    0.37
     Kok
    0.36
    тного
    0.36
    тию
    0.35
     ky
    0.34
     Nel
    0.34
     mydict
    0.34
     एक्स
    0.34
    Activations Density 0.001%

    No Known Activations