© 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. 223765
    Prev
    Next
    INDEX
    Explanations

    un.org links

    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_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
    s
    0.42
    m
    0.39
    л
    0.34
    ITIVE
    0.33
    <unused292>
    0.31
    투자
    0.30
     cré
    0.30
    u
    0.30
    t
    0.29
    벍
    0.29
    POSITIVE LOGITS
    。
    0.42
    ON
    0.32
    ure
    0.30
    ה
    0.30
    ols
    0.29
    ↵↵
    0.29
     as
    0.28
    </sup>
    0.28
     (
    0.28
    ون
    0.27
    Activations Density 0.003%

    No Known Activations