© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214575
    Prev
    Next
    INDEX
    Explanations

    array usage in code

    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_5_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
    ра
    1.45
    。
    1.35
    t
    1.23
    ли
    1.14
    ार
    1.05
    ных
    1.02
    に
    1.00
    り
    0.99
    to
    0.98
    える
    0.98
    POSITIVE LOGITS
     êtes
    1.23
     habitudes
    1.15
    ক
    1.02
     équipes
    1.01
     spindles
    1.01
     ateliers
    1.00
     empêcher
    0.99
    :
    0.98
    nél
    0.98
    naires
    0.98
    Activations Density 0.001%

    No Known Activations