© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61212
    Prev
    Next
    INDEX
    Explanations

    Again and again

    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_11_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
     zwią
    0.61
     shew
    0.61
     sincer
    0.59
    ब
    0.57
    το
    0.57
    Το
    0.57
    美国
    0.56
    雒
    0.56
     compris
    0.55
     objectifs
    0.55
    POSITIVE LOGITS
     fragile
    0.62
    nov
    0.57
     in
    0.57
    assador
    0.55
    ሮችን
    0.55
    enden
    0.55
    </h3>
    0.53
    ่อน
    0.52
     fragmented
    0.52
    ِد
    0.52
    Activations Density 0.001%

    No Known Activations