© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90639
    Prev
    Next
    INDEX
    Explanations

    Telus, international, ken

    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_3_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
    t
    0.98
    lara
    0.82
    ages
    0.70
    l
    0.68
    _
    0.68
     совета
    0.68
    lation
    0.66
    j
    0.62
    nd
    0.61
    liness
    0.61
    POSITIVE LOGITS
    í
    0.77
    ü
    0.73
    ется
    0.71
    ینک
    0.71
     finely
    0.65
    ing
    0.63
    oč
    0.63
     विरुद्ध
    0.63
    toFixed
    0.62
    ۴
    0.62
    Activations Density 0.000%

    No Known Activations