© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47410
    Prev
    Next
    INDEX
    Explanations

    code comments and setup instructions

    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_10_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
    ↵
    0.52
    ous
    0.49
    ០
    0.49
     gravité
    0.48
    zechoslovak
    0.47
     have
    0.47
     ample
    0.47
    ]{
    0.46
    seca
    0.46
     haue
    0.45
    POSITIVE LOGITS
    ي
    0.75
    ول
    0.59
    다
    0.59
    ر
    0.56
    ை
    0.56
    אס
    0.56
    ர்
    0.55
    र
    0.55
    ค
    0.55
    ال
    0.54
    Activations Density 0.091%

    No Known Activations