© 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. 36723
    Prev
    Next
    INDEX
    Explanations

    klar

    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
    ת
    0.71
     perceber
    0.70
    اب
    0.63
    ח
    0.60
     hareket
    0.59
     garantizar
    0.57
     realize
    0.56
    人
    0.56
     handicap
    0.55
     primeiro
    0.55
    POSITIVE LOGITS
     네
    0.57
     ā
    0.54
    èses
    0.52
     )-
    0.52
    iliated
    0.51
    )))
    0.50
    ′,
    0.50
    plets
    0.50
     Ō
    0.50
    一股
    0.50
    Activations Density 0.000%

    No Known Activations