© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4746
    Prev
    Next
    INDEX
    Explanations

    reset to default

    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_40_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
     productImage
    0.39
    Ż
    0.37
     poln
    0.37
     ويل
    0.36
     schwer
    0.35
     previewBuilder
    0.35
    呜
    0.35
    𝙳
    0.35
     ganze
    0.34
     вікі
    0.34
    POSITIVE LOGITS
     default
    0.64
     defaults
    0.56
    Returning
    0.55
     returning
    0.54
    Default
    0.52
     back
    0.51
    default
    0.50
     Default
    0.50
     вернуться
    0.47
     stock
    0.46
    Activations Density 0.002%

    No Known Activations