© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167577
    Prev
    Next
    INDEX
    Explanations

    RFC and protocols

    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_31_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
     drowned
    0.34
     reused
    0.34
     Израи
    0.33
     salty
    0.33
    तु
    0.31
    튠
    0.31
     deities
    0.31
    Guinea
    0.31
     mengh
    0.30
     kalt
    0.30
    POSITIVE LOGITS
    RFC
    0.39
     RFC
    0.34
     "*************"
    0.32
    omat
    0.30
     [
    0.29
     Conver
    0.29
    arlama
    0.29
    략
    0.29
    rfc
    0.29
     College
    0.29
    Activations Density 0.002%

    No Known Activations