© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6109
    Prev
    Next
    INDEX
    Explanations

    Romanian, Italian, German, Hebrew place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     fieldContext
    0.37
     बरेली
    0.37
    anken
    0.35
    erman
    0.35
    amless
    0.35
    েরিক
    0.35
    З
    0.34
    賞
    0.34
     overarching
    0.34
    oring
    0.34
    POSITIVE LOGITS
    Lincoln
    0.48
     Lincolnshire
    0.46
     Lincoln
    0.42
     খাঁ
    0.38
    ראש
    0.37
    support
    0.35
    vej
    0.34
     sugli
    0.34
    pectral
    0.34
     sympathy
    0.33
    Activations Density 0.020%

    No Known Activations