© 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. 258402
    Prev
    Next
    INDEX
    Explanations

    "of" followed by data descriptors

    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
     sights
    0.28
     Musik
    0.27
    銑
    0.27
     intoler
    0.27
     "
    0.26
     absurd
    0.26
     Seguridad
    0.26
     بابەت
    0.26
    MinIntensity
    0.26
     untenable
    0.25
    POSITIVE LOGITS
    ೬
    0.31
    лке
    0.29
    jších
    0.29
     коллек
    0.29
    ITAS
    0.29
     sétimo
    0.28
    쿤
    0.28
    ειας
    0.28
    рии
    0.28
     সংগ্রামে
    0.28
    Activations Density 0.014%

    No Known Activations