© 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. 10075
    Prev
    Next
    INDEX
    Explanations

    TV shows

    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
    <0x91>
    0.54
     સમસ્યા
    0.53
     ScriptInterface
    0.53
     సమస్య
    0.53
     jų
    0.52
     Bupati
    0.51
    篡
    0.51
     ব্যপারে
    0.51
    ూరు
    0.50
     他们
    0.50
    POSITIVE LOGITS
    \
    0.60
    nb
    0.60
    NBC
    0.59
    Television
    0.59
    Ш
    0.58
    tt
    0.57
    nn
    0.56
    TV
    0.55
    q
    0.55
    all
    0.53
    Activations Density 0.028%

    No Known Activations