© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229686
    Prev
    Next
    INDEX
    Explanations

    Adélie, Gentoo, Ghent, Coffman

    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_6_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
    1.58
    ade
    1.37
    b
    1.31
    ed
    1.14
    ol
    1.14
    i
    1.14
    '
    1.08
    es
    1.06
    ant
    1.03
    er
    1.00
    POSITIVE LOGITS
    ви
    1.11
     construit
    0.95
     реали
    0.95
    в
    0.95
    𝙡
    0.94
     бъде
    0.88
     сово
    0.85
    нку
    0.84
     toekom
    0.84
     gérer
    0.83
    Activations Density 0.000%

    No Known Activations