© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30390
    Prev
    Next
    INDEX
    Explanations

    SAP, eye, AI, YouTube

    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_7_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
    end
    0.47
    c
    0.46
     Introduction
    0.45
    he
    0.44
    ão
    0.43
     Solutions
    0.43
    adays
    0.43
     Resources
    0.42
    ↵↵
    0.42
     Study
    0.41
    POSITIVE LOGITS
     marketplaces
    0.50
     receptacles
    0.50
    اری
    0.49
     dictators
    0.48
     saranam
    0.48
     isos
    0.47
     acacia
    0.46
     inciner
    0.46
     nightclubs
    0.46
     auxqu
    0.46
    Activations Density 0.002%

    No Known Activations