© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157455
    Prev
    Next
    INDEX
    Explanations

    Kon, Kol, Kau, Kan

    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_2_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
     for
    1.50
    0
    1.25
    。
    1.22
    ၀
    1.16
    1.13
    ０
    1.09
    টি
    1.09
     from
    1.06
    ।'
    1.05
    গ
    1.04
    POSITIVE LOGITS
    ка
    1.11
    alta
    1.04
    тно
    1.02
    ier
    1.01
    far
    0.98
    ние
    0.96
    ffic
    0.96
    ure
    0.95
    sters
    0.94
    اً
    0.93
    Activations Density 0.000%

    No Known Activations