© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 244654
    Prev
    Next
    INDEX
    Explanations

    fold in half or thirds

    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
     representa
    0.43
     représente
    0.42
    Closure
    0.36
    堯
    0.36
     Record
    0.36
     représentent
    0.36
     शहद
    0.36
    )$,
    0.36
    Record
    0.36
     representan
    0.36
    POSITIVE LOGITS
     unfit
    0.38
    苕
    0.38
     outfit
    0.37
    וא
    0.36
     bound
    0.36
     outfits
    0.35
    র্য
    0.34
     آپریشن
    0.34
     tratti
    0.34
    BOUND
    0.34
    Activations Density 0.002%

    No Known Activations