© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208411
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     five
    0.49
     cinco
    0.48
    ៥
    0.45
     trente
    0.44
     fives
    0.44
    ৫
    0.43
     fifty
    0.42
     cinque
    0.42
     다섯
    0.42
     methods
    0.42
    POSITIVE LOGITS
     child
    0.79
    child
    0.75
    Child
    0.73
     Child
    0.64
     CHILD
    0.64
     kid
    0.63
     ребенок
    0.57
    子
    0.57
     ребён
    0.52
     ребен
    0.52
    Activations Density 0.001%

    No Known Activations