© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82712
    Prev
    Next
    INDEX
    Explanations

    CO₂ and COALESCE

    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_0_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
    ور
    1.37
     dàng
    1.30
    ्यक्रम
    1.27
    이지만
    1.21
    َا
    1.18
     avut
    1.13
     I
    1.11
    를
    1.11
    aks
    1.09
    ams
    1.06
    POSITIVE LOGITS
    i
    3.02
    an
    2.42
    n
    2.36
    t
    2.27
    ي
    2.20
    ed
    2.19
    r
    2.13
    er
    2.09
    in
    1.99
    a
    1.98
    Activations Density 0.001%

    No Known Activations