© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91981
    Prev
    Next
    INDEX
    Explanations

    tonight or speaker followed by punctuation

    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_11_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
    য়াছে
    0.29
     alkalies
    0.29
    Ｏ
    0.28
     remedied
    0.28
    Ｍ
    0.28
     samedi
    0.28
    ванович
    0.28
    ﹕
    0.27
    Ẳ
    0.27
     거고
    0.27
    POSITIVE LOGITS
    n
    0.31
    k
    0.28
     de
    0.27
    ani
    0.27
    r
    0.26
    '
    0.26
    ists
    0.26
    ling
    0.25
     diver
    0.25
    heads
    0.25
    Activations Density 0.002%

    No Known Activations