© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 206762
    Prev
    Next
    INDEX
    Explanations

    deserve rights, exploration of, having to

    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_25_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
     Neal
    0.35
    他
    0.34
    zz
    0.34
     ခု
    0.31
     experience
    0.30
     spectrum
    0.30
     насе
    0.30
     він
    0.29
     energies
    0.29
    Bare
    0.29
    POSITIVE LOGITS
    ﮄ
    0.35
     fon
    0.34
     ಜೆ
    0.33
    すら
    0.32
    フォ
    0.32
    isHidden
    0.32
    ponential
    0.31
     incon
    0.31
     ninguém
    0.31
     fools
    0.31
    Activations Density 0.028%

    No Known Activations