© 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. 45026
    Prev
    Next
    INDEX
    Explanations

    planets

    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
     subsidi
    0.43
     이르
    0.43
     lactis
    0.41
     guter
    0.39
     catatan
    0.38
    ܂
    0.38
    sessionId
    0.38
     reyes
    0.38
    یدم
    0.38
     weiterhin
    0.38
    POSITIVE LOGITS
    安裝
    0.43
    वाई
    0.42
     Installation
    0.41
     GET
    0.41
    </
    0.41
    ડા
    0.41
    瘦
    0.41
    安装
    0.40
     Uninstall
    0.39
    لو
    0.39
    Activations Density 0.000%

    No Known Activations