© 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. 161590
    Prev
    Next
    INDEX
    Explanations

    runoff election

    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
    و
    1.25
    కు
    1.12
    ly
    1.06
    Count
    1.00
    ate
    0.98
    h
    0.96
    ul
    0.96
    ge
    0.95
    in
    0.95
    ut
    0.94
    POSITIVE LOGITS
    ה
    1.43
     can
    1.17
     воздей
    1.16
    هي
    1.15
     сражение
    1.13
    המ
    1.09
     recipiente
    1.08
     র
    1.07
     coordinador
    1.07
    ي
    1.07
    Activations Density 0.001%

    No Known Activations