© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119355
    Prev
    Next
    INDEX
    Explanations

    internal and external

    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
     Zeitschr
    0.33
    士
    0.32
    𝘩
    0.31
    ພວກເຮ
    0.30
     betroffen
    0.30
    နာ
    0.30
    সুতরাং
    0.30
    喈
    0.30
    રમાં
    0.29
    शत
    0.29
    POSITIVE LOGITS
     years
    0.32
     Ivory
    0.31
     someday
    0.29
    quisitions
    0.29
     possible
    0.28
     strip
    0.28
     '
    0.28
    vastatin
    0.27
     Bowen
    0.27
    বিহীন
    0.27
    Activations Density 0.004%

    No Known Activations