© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129956
    Prev
    Next
    INDEX
    Explanations

    Paul

    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_50_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
    ἥ
    0.43
    gares
    0.41
    Helper
    0.39
    зова
    0.39
    Nuestro
    0.38
    gent
    0.38
     zusätzliche
    0.37
     nearest
    0.37
    DFT
    0.37
     റ
    0.37
    POSITIVE LOGITS
    fold
    0.39
     Fold
    0.39
     শুনেছি
    0.37
     folds
    0.37
    匚
    0.37
    BJ
    0.36
     fold
    0.36
     বিছ
    0.36
    oddsidemargin
    0.36
     BJ
    0.35
    Activations Density 0.000%

    No Known Activations