© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207104
    Prev
    Next
    INDEX
    Explanations

    scheduling or timing adjustments

    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_19_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
    BetMap
    0.47
    жета
    0.46
     показатели
    0.45
    דם
    0.44
    בודה
    0.44
     отдельные
    0.43
    纰
    0.43
    ץ
    0.43
    لمات
    0.42
     entidades
    0.42
    POSITIVE LOGITS
     laptop
    0.60
     by
    0.58
     theses
    0.50
     meet
    0.50
     worker
    0.49
     keyboard
    0.49
     reschedule
    0.48
     chat
    0.47
     printer
    0.47
     lunch
    0.46
    Activations Density 0.000%

    No Known Activations