© 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. 56520
    Prev
    Next
    INDEX
    Explanations

    committed to

    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
    June
    0.66
    ।
    0.65
     Data
    0.64
     Executive
    0.62
    ą
    0.61
    ן
    0.61
    July
    0.60
    April
    0.60
     Special
    0.59
    I
    0.59
    POSITIVE LOGITS
     እንደሚ
    0.61
     κατα
    0.60
     difficiles
    0.60
     حيث
    0.59
     живота
    0.54
     canceled
    0.53
     الَّ
    0.53
     обо
    0.52
     зо
    0.52
     μεγά
    0.52
    Activations Density 0.001%

    No Known Activations