© 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. 248734
    Prev
    Next
    INDEX
    Explanations

    equals

    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
     A
    0.40
     Multi
    0.40
     difference
    0.39
     five
    0.37
     Difference
    0.36
    šek
    0.36
     BRIEF
    0.36
     В
    0.36
    ုံ
    0.36
     multi
    0.36
    POSITIVE LOGITS
     इक्वल
    0.45
    ILING
    0.41
    等于
    0.41
     Marked
    0.41
     равен
    0.39
     obil
    0.38
     recc
    0.36
    迠
    0.36
     তব
    0.35
    밟
    0.35
    Activations Density 0.003%

    No Known Activations