© 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. 90583
    Prev
    Next
    INDEX
    Explanations

    Kartini Day, Karthik, sushi, Carthage, Dota

    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
     on
    0.80
    .
    0.77
     for
    0.70
    ed
    0.69
     be
    0.68
     f
    0.67
     The
    0.67
     the
    0.66
     reorgan
    0.63
     a
    0.61
    POSITIVE LOGITS
    لی
    0.73
    ната
    0.68
    ’
    0.67
    ics
    0.60
    اک
    0.60
    ق
    0.59
    нима
    0.59
     específicas
    0.59
    osas
    0.57
     ಪ್ರಮಾಣ
    0.57
    Activations Density 0.000%

    No Known Activations