© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196798
    Prev
    Next
    INDEX
    Explanations

    time quantifiers and locations

    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_27_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
     conformational
    0.40
     Lockdown
    0.39
     propag
    0.38
    谠
    0.38
     Charts
    0.38
     Computational
    0.37
     playwright
    0.37
     Dynamic
    0.37
     কলেরা
    0.37
     Automated
    0.37
    POSITIVE LOGITS
     。
    0.40
    。
    0.40
    .–
    0.37
     kter
    0.37
    .--
    0.36
    |
    0.36
    。”
    0.35
    ._
    0.35
    。《
    0.35
     မြ
    0.34
    Activations Density 0.000%

    No Known Activations