© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14745
    Prev
    Next
    INDEX
    Explanations

    early stopping

    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_34_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
    LogLevel
    0.42
     nylon
    0.37
    ्हे
    0.36
     trail
    0.35
     Schne
    0.35
    घाटन
    0.34
     दुआ
    0.34
    נ
    0.34
    滝
    0.34
    poi
    0.33
    POSITIVE LOGITS
     verbess
    0.44
     शरी
    0.40
    epoch
    0.40
     मै
    0.40
     ગો
    0.39
     state
    0.38
     Improved
    0.38
     obdob
    0.38
     improved
    0.38
     Saba
    0.36
    Activations Density 0.039%

    No Known Activations