© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233239
    Prev
    Next
    INDEX
    Explanations

    data class

    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_32_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
    禿
    0.36
    velle
    0.35
     pijn
    0.35
    줘
    0.35
    zieh
    0.35
    ิ่ง
    0.35
    ützt
    0.34
     messy
    0.34
     bruke
    0.34
     include
    0.34
    POSITIVE LOGITS
     起
    0.39
    慜
    0.38
    ٗ
    0.38
     waking
    0.37
    ANGMAR
    0.37
    互联网档案馆
    0.37
    лий
    0.36
    Bhar
    0.36
     Gow
    0.36
    Tib
    0.36
    Activations Density 0.000%

    No Known Activations