© 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. 232586
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
    of
    0.96
     of
    0.93
    σ
    0.91
     as
    0.90
    적
    0.90
     have
    0.80
     has
    0.80
    вер
    0.79
    이고
    0.79
     abbia
    0.79
    POSITIVE LOGITS
    5
    0.94
    ЛЕ
    0.89
    r
    0.88
    ر
    0.88
    ৫
    0.88
    il
    0.86
    रेशन
    0.80
    ۔
    0.80
    4
    0.80
    1
    0.79
    Activations Density 0.000%

    No Known Activations