© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143293
    Prev
    Next
    INDEX
    Explanations

    Italian words

    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_46_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
     sor
    0.43
     قسم
    0.39
    ymen
    0.39
    矛
    0.38
    喈
    0.38
     ValidationError
    0.38
     Sor
    0.38
     Tat
    0.37
    ौनक
    0.37
    ypse
    0.37
    POSITIVE LOGITS
    ita
    0.90
    ITA
    0.84
     ITA
    0.64
     ita
    0.58
    <0x8A>
    0.54
     Ita
    0.54
    itsa
    0.50
    itza
    0.49
    itele
    0.48
    hita
    0.45
    Activations Density 0.004%

    No Known Activations