© 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
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90773
    Prev
    Next
    INDEX
    Explanations

    assess document validate

    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_60_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
     A
    0.53
     Older
    0.50
     Reverse
    0.43
     SELF
    0.43
     которых
    0.43
     ইয়
    0.42
     JUST
    0.42
     който
    0.42
     Вай
    0.41
     Sistemas
    0.41
    POSITIVE LOGITS
    ↵↵
    0.58
    ↵
    0.52
    for
    0.51
     for
    0.49
    !
    0.49
    ↵↵↵↵
    0.48
    ↵↵↵
    0.48
    Don
    0.44
    ！
    0.43
    зал
    0.40
    Activations Density 0.013%

    No Known Activations