© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42125
    Prev
    Next
    INDEX
    Explanations

    let us

    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_22_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
    दों
    0.41
    孑
    0.37
    迤
    0.36
     aas
    0.36
    widgetTo
    0.36
     oldukça
    0.35
     otáz
    0.35
    丏
    0.35
    শ্রুতি
    0.34
    रों
    0.34
    POSITIVE LOGITS
     ভাইকে
    0.40
     fruition
    0.38
    ěk
    0.38
    セレ
    0.37
    incinnati
    0.36
     Marshall
    0.35
    Marshall
    0.35
    all
    0.35
    ong
    0.35
     tour
    0.35
    Activations Density 0.004%

    No Known Activations