© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126764
    Prev
    Next
    INDEX
    Explanations

    special characters and code delimiters

    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_37_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
     তোলে
    0.38
    ethoscope
    0.38
    othermic
    0.37
     સમસ્યા
    0.36
    僑
    0.36
    fortun
    0.35
     harb
    0.35
     männer
    0.35
    yscanner
    0.35
    ähler
    0.35
    POSITIVE LOGITS
    ेश्च
    0.41
     RSW
    0.41
    主
    0.39
    单独
    0.38
    INGTON
    0.37
     জায়
    0.37
    崇
    0.37
     చూప
    0.36
    lest
    0.35
     DRS
    0.35
    Activations Density 0.001%

    No Known Activations