© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209271
    Prev
    Next
    INDEX
    Explanations

    location convenience

    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
    磨
    0.45
     glued
    0.42
    粖
    0.41
    лії
    0.40
     despised
    0.40
    ステム
    0.39
    cluse
    0.38
    Ϻ
    0.38
    BeerItem
    0.37
    Clicked
    0.37
    POSITIVE LOGITS
     देण्यात
    0.47
     porta
    0.47
     опять
    0.45
     fuel
    0.45
    </strong>
    0.45
    ax
    0.44
    ainya
    0.44
    oggler
    0.43
    fuel
    0.42
    coll
    0.42
    Activations Density 0.000%

    No Known Activations