© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132909
    Prev
    Next
    INDEX
    Explanations

    jornada, terreno, significativa

    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_1_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
    .
    0.97
     carri
    0.95
    ;
    0.89
     trucking
    0.88
     fisheries
    0.86
     foodie
    0.86
     rookie
    0.86
     conveyor
    0.86
     teller
    0.85
     jogging
    0.84
    POSITIVE LOGITS
    ي
    1.61
    h
    1.50
    t
    1.49
    f
    1.38
    ري
    1.34
    ם
    1.34
    ট
    1.28
    لي
    1.26
    ли
    1.24
    ير
    1.22
    Activations Density 0.002%

    No Known Activations