© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57739
    Prev
    Next
    INDEX
    Explanations

    punctuation or versions

    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_59_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
     мое
    0.42
    ăl
    0.39
     TripAdvisor
    0.38
    oggling
    0.38
     ਖ
    0.38
    applying
    0.38
    my
    0.38
    YouTube
    0.37
    Twitter
    0.36
     Tumblr
    0.36
    POSITIVE LOGITS
     </
    0.50
     version
    0.49
     Version
    0.46
    Version
    0.45
     "**
    0.45
    !</
    0.44
     '''
    0.43
     '*
    0.43
    ~~~~
    0.42
    version
    0.41
    Activations Density 0.009%

    No Known Activations