© 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. 107522
    Prev
    Next
    INDEX
    Explanations

    'ke', 'kem', 'kev', 'g', 'arid' beginnings

    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
    ۹
    1.39
    ৫
    1.05
    自己
    0.95
    stop
    0.88
    0.88
     It
    0.85
    de
    0.85
    reviews
    0.85
    er
    0.84
    想想
    0.84
    POSITIVE LOGITS
    '
    1.27
    는
    1.13
     که
    1.05
    า
    1.01
    ール
    0.94
    ла
    0.94
     conteú
    0.93
    '%(
    0.91
     circunferência
    0.91
    くらい
    0.90
    Activations Density 0.000%

    No Known Activations