© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231763
    Prev
    Next
    INDEX
    Explanations

    learned behavior

    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_6_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
    1.08
    ir
    1.00
     nær
    0.97
    _
    0.94
    hi
    0.93
     matem
    0.92
    مر
    0.91
     arbete
    0.86
     They
    0.85
    حد
    0.84
    POSITIVE LOGITS
    asının
    1.07
     swojego
    1.05
    ul
    0.96
    ת
    0.95
    ри
    0.95
    elor
    0.94
    ou
    0.93
    ți
    0.92
    arının
    0.92
    anın
    0.91
    Activations Density 0.000%

    No Known Activations