© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207974
    Prev
    Next
    INDEX
    Explanations

    engine

    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_20_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
     irrever
    0.42
    }\,
    0.40
    ò
    0.40
     Mac
    0.39
     написано
    0.39
     Macs
    0.39
     mắc
    0.38
    isn
    0.38
     angrily
    0.37
    isr
    0.37
    POSITIVE LOGITS
    remia
    0.49
     paramount
    0.46
     paradig
    0.44
    вера
    0.42
     chem
    0.42
    лів
    0.41
     Samurai
    0.41
    崂
    0.41
     japanese
    0.41
    encja
    0.41
    Activations Density 0.000%

    No Known Activations