© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17329
    Prev
    Next
    INDEX
    Explanations

    database connection errors

    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
    ientôt
    0.39
    檜
    0.39
     Rv
    0.39
    Oj
    0.38
    Roxy
    0.38
    个性
    0.38
    DialogOpen
    0.38
    MyISAM
    0.38
    rops
    0.37
    铵
    0.36
    POSITIVE LOGITS
     Constantine
    0.42
     Quinn
    0.42
     SG
    0.40
     Cos
    0.39
     Doc
    0.38
     frequencies
    0.38
     Phillip
    0.37
     doc
    0.37
     Kernel
    0.36
     Seventeen
    0.36
    Activations Density 0.022%

    No Known Activations