© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110347
    Prev
    Next
    INDEX
    Explanations

    Omeprazol, Bepanthen, Pap

    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_2_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
    k
    1.36
     as
    1.33
     by
    1.30
     was
    1.13
     but
    1.06
    ,
    1.05
    j
    1.03
     so
    1.01
    ene
    0.99
    kta
    0.99
    POSITIVE LOGITS
    ۔
    1.70
    ።
    1.22
    ב
    1.16
    It
    1.13
    ும்
    1.05
    ור
    1.02
    ι
    1.02
    کن
    1.00
    。
    1.00
    는
    0.99
    Activations Density 0.000%

    No Known Activations