© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6484
    Prev
    Next
    INDEX
    Explanations

    key improvements

    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_40_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
    ალური
    0.42
     explanations
    0.40
    amay
    0.38
    (".");
    0.37
    𒋫
    0.37
     docket
    0.37
    examin
    0.36
    ictionaries
    0.35
    тили
    0.35
    IFICATIONS
    0.35
    POSITIVE LOGITS
     Rejected
    0.39
     पीएचडी
    0.39
     ইত
    0.39
     mengaku
    0.38
    Readable
    0.38
     memang
    0.37
     தோல்
    0.37
     Renata
    0.37
    鐒
    0.36
     Hasil
    0.36
    Activations Density 0.044%

    No Known Activations