© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109995
    Prev
    Next
    INDEX
    Explanations

    aloof

    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
    .
    1.52
    е
    1.37
    и
    1.36
    he
    1.13
    ц
    1.08
     необходи
    1.07
     ذریع
    1.07
     are
    1.05
    та
    1.04
    co
    1.04
    POSITIVE LOGITS
    ’
    1.27
    -
    1.23
    কে
    1.13
    सँग
    1.05
    د
    1.02
    ‘
    0.98
         
    0.95
    i
    0.95
    '
    0.93
     Kähler
    0.92
    Activations Density 0.001%

    No Known Activations