© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182756
    Prev
    Next
    INDEX
    Explanations

    during file processing

    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_29_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
     зави
    0.40
    乀
    0.37
     referentes
    0.36
    ኢ
    0.36
     zem
    0.35
     seules
    0.34
     pecado
    0.34
     trending
    0.33
    navbarSupported
    0.33
    ết
    0.33
    POSITIVE LOGITS
     Hydro
    0.39
     گوگل
    0.38
     :-)
    0.37
     Mobil
    0.36
     trimethyl
    0.36
     MOB
    0.36
    +//
    0.36
     TabLayout
    0.36
    +"','"+
    0.35
     McCabe
    0.35
    Activations Density 0.003%

    No Known Activations