© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9512
    Prev
    Next
    INDEX
    Explanations

    guiding to success

    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_13_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
    प
    0.28
     $>$
    0.26
    пенди
    0.26
     pedir
    0.25
    '))
    0.25
    шали
    0.24
     oreille
    0.24
    нима
    0.24
    Venue
    0.24
    ग
    0.24
    POSITIVE LOGITS
    sters
    0.30
     flushing
    0.30
     தொடர்ப
    0.29
    them
    0.29
    nell
    0.28
     Wittgenstein
    0.27
    ınızı
    0.27
     hrvats
    0.27
     نظری
    0.27
    stering
    0.26
    Activations Density 0.110%

    No Known Activations