© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234509
    Prev
    Next
    INDEX
    Explanations

    Italian medical contexts

    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
     taglio
    0.45
    atiche
    0.44
    nez
    0.42
    itti
    0.41
    atrice
    0.40
    vati
    0.40
    avano
    0.39
    }{-
    0.38
     meccan
    0.38
     istit
    0.38
    POSITIVE LOGITS
     perteneciente
    0.38
    ؒ
    0.38
    oretum
    0.37
    อล
    0.37
    Taking
    0.36
     наш
    0.36
     леген
    0.36
    ᱦ
    0.36
    язви
    0.35
     Tow
    0.35
    Activations Density 0.000%

    No Known Activations