© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19400
    Prev
    Next
    INDEX
    Explanations

    edges connecting entities

    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_15_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
    0.66
    ha
    0.66
    1
    0.61
    à
    0.57
    Ha
    0.56
    ga
    0.55
     à
    0.55
    çi
    0.54
    6
    0.54
    À
    0.54
    POSITIVE LOGITS
    setBadgeText
    0.52
     UIColor
    0.52
    LetterGrade
    0.49
    OST
    0.48
    ндагы
    0.48
     Antrieb
    0.48
     состоя
    0.48
    setIcon
    0.48
    ﻻ
    0.48
     ತೊ
    0.47
    Activations Density 0.005%

    No Known Activations