© 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. 5048
    Prev
    Next
    INDEX
    Explanations

    path to concepts/words

    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
     Joaquin
    0.39
    Campus
    0.39
     Campus
    0.38
     Joker
    0.38
     ово
    0.37
    Snackbar
    0.37
     BOW
    0.37
    妽
    0.37
    excellence
    0.37
     caballero
    0.36
    POSITIVE LOGITS
    finder
    0.40
     Warm
    0.39
    findElement
    0.39
    依赖
    0.38
    ił
    0.37
    ாதை
    0.37
     Dependency
    0.37
     integral
    0.37
    dependency
    0.37
    portal
    0.36
    Activations Density 0.013%

    No Known Activations