© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50249
    Prev
    Next
    INDEX
    Explanations

    is a condition

    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_31_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
    ellikle
    0.34
     последова
    0.32
     constamment
    0.31
    มนเชสเตอร์
    0.31
     özellikle
    0.31
     atypical
    0.30
     Relativity
    0.30
    $[
    0.30
     spezi
    0.30
     Relatively
    0.30
    POSITIVE LOGITS
     ошиб
    0.37
     soul
    0.37
    灵魂
    0.35
    рим
    0.34
    Ꭴ
    0.33
    误
    0.32
     ভুল
    0.32
     vrai
    0.31
     appropriation
    0.31
     mistaken
    0.31
    Activations Density 0.014%

    No Known Activations