© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5004
    Prev
    Next
    INDEX
    Explanations

    dart code

    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_38_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
    иск
    0.38
    integration
    0.36
    besie
    0.35
    ულ
    0.35
    entr
    0.35
    <!
    0.34
    ≣
    0.34
     Translated
    0.34
    肅
    0.34
    டிய
    0.34
    POSITIVE LOGITS
     late
    0.60
    late
    0.46
     mante
    0.46
     στά
    0.42
     позд
    0.41
     Gareth
    0.41
     обна
    0.40
    晚
    0.40
     Late
    0.39
    ándolo
    0.39
    Activations Density 0.021%

    No Known Activations