© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106252
    Prev
    Next
    INDEX
    Explanations

    sh followed by non-English syllable

    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_1_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
     of
    1.36
     to
    1.24
     y
    1.16
     are
    1.16
     d
    1.02
     at
    1.02
     you
    1.01
     with
    1.00
     که
    1.00
     o
    0.99
    POSITIVE LOGITS
    an
    1.94
    on
    1.75
    it
    1.70
    is
    1.67
    il
    1.58
    a
    1.53
    ad
    1.49
    n
    1.49
    ar
    1.48
    ,
    1.41
    Activations Density 0.001%

    No Known Activations