© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113124
    Prev
    Next
    INDEX
    Explanations

    S followed by Italian words

    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_2_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
    টি
    1.09
    OT
    1.04
    N
    0.96
    ET
    0.96
    F
    0.96
    US
    0.94
    u
    0.93
    ഇ
    0.93
    Index
    0.91
    .
    0.91
    POSITIVE LOGITS
     can
    0.97
    но
    0.96
    ก
    0.94
    ная
    0.80
     меня
    0.77
     perceptive
    0.77
     rematch
    0.75
    ۰
    0.75
     в
    0.73
    ва
    0.72
    Activations Density 0.000%

    No Known Activations