© 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. 2343
    Prev
    Next
    INDEX
    Explanations

    @app

    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
    城
    0.38
    ）【
    0.37
     বিগ
    0.36
     COLLATION
    0.36
    𝟎
    0.35
     diffe
    0.35
     مصروف
    0.34
    omir
    0.34
    は大
    0.34
     cof
    0.33
    POSITIVE LOGITS
     l
    0.37
     Teilnehmer
    0.36
    property
    0.36
    anjan
    0.35
    шта
    0.34
     Navi
    0.33
     Fabi
    0.33
    ênio
    0.33
     property
    0.33
    enda
    0.33
    Activations Density 0.002%

    No Known Activations