© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198801
    Prev
    Next
    INDEX
    Explanations

    reporting issues or findings

    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_27_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
    lista
    0.38
    usu
    0.35
    ny
    0.34
    itore
    0.34
    azion
    0.34
    url
    0.32
     里
    0.32
    giz
    0.32
    ide
    0.32
    里
    0.32
    POSITIVE LOGITS
    玫瑰
    0.34
     minced
    0.34
     vormen
    0.34
     mesenchymal
    0.33
     remplacement
    0.33
     herringbone
    0.32
     sostit
    0.32
     faint
    0.32
     melting
    0.32
     mél
    0.31
    Activations Density 0.002%

    No Known Activations