© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97586
    Prev
    Next
    INDEX
    Explanations

    ure

    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_14_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
    "
    0.65
    ס
    0.60
    س
    0.54
    А
    0.53
    ສຸດ
    0.52
    ЕН
    0.51
    П
    0.50
    ﺮ
    0.50
    Hom
    0.50
    느
    0.49
    POSITIVE LOGITS
     Verfahren
    0.60
     Occasionally
    0.58
     Σε
    0.57
     Wasch
    0.56
     inconvén
    0.55
     Wanneer
    0.54
    ~(
    0.54
    occ
    0.53
     Stelle
    0.53
     Fahrt
    0.52
    Activations Density 0.000%

    No Known Activations