© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27171
    Prev
    Next
    INDEX
    Explanations

    throughout the day/week/process

    np_acts-logits-general · gemini-2.5-flash-lite

    throughout

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    phrases related to language and grammar precision.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    𝗼
    0.64
    𝗰
    0.64
     ね
    0.64
    ‌تر
    0.64
    𝗿
    0.63
    ٤
    0.62
    kyverno
    0.61
     چ
    0.60
    स्पर
    0.60
     ਰ
    0.60
    POSITIVE LOGITS
    to
    0.80
    ل
    0.78
    z
    0.73
    ו
    0.73
    h
    0.73
    The
    0.72
    (
    0.71
    Add
    0.70
    State
    0.69
    May
    0.68
    Activations Density 0.005%

    No Known Activations