© 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. 198418
    Prev
    Next
    INDEX
    Explanations

    syndrome or hepatitis

    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
    あ
    0.57
    ة
    0.56
    KL
    0.54
    ды
    0.52
    యం
    0.52
    阅
    0.52
    [
    0.52
     experiencing
    0.50
    过
    0.50
    他
    0.50
    POSITIVE LOGITS
    maketitle
    0.55
     talleres
    0.52
     baloncesto
    0.51
     incentiv
    0.50
     gyms
    0.50
    erné
    0.48
     spiega
    0.48
     quiere
    0.47
     largement
    0.47
     crescita
    0.47
    Activations Density 0.000%

    No Known Activations