© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137040
    Prev
    Next
    INDEX
    Explanations

    I followed by ' or have/believe

    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_12_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
    د
    0.53
     educators
    0.52
     discourses
    0.52
    copies
    0.52
    c
    0.52
     Siddhartha
    0.51
     hectares
    0.50
     enseignants
    0.50
     artistes
    0.50
     universities
    0.50
    POSITIVE LOGITS
    ız
    0.58
    ódio
    0.57
    َهُ
    0.55
    ínt
    0.55
    麽
    0.55
     بینی
    0.54
    мости
    0.54
    ymmetry
    0.53
    ós
    0.52
    ませ
    0.52
    Activations Density 0.001%

    No Known Activations