© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13282
    Prev
    Next
    INDEX
    Explanations

    public

    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_40_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
    ছুর
    0.43
    ческое
    0.40
    offe
    0.36
    borist
    0.35
     Branding
    0.35
    詎
    0.35
     Notepad
    0.35
    unstyled
    0.34
    plat
    0.34
    catch
    0.34
    POSITIVE LOGITS
     PUBLIC
    0.55
     Public
    0.51
     публи
    0.51
     public
    0.48
    Public
    0.48
    PUBLIC
    0.46
     publiques
    0.44
     公
    0.44
    public
    0.43
     общественных
    0.43
    Activations Density 0.011%

    No Known Activations