© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103320
    Prev
    Next
    INDEX
    Explanations

    Latin/Greek suffixes

    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
    یس
    1.24
     be
    1.23
    是我们
    1.16
     as
    1.14
    ని
    1.08
    ني
    1.08
     a
    1.05
    مع
    1.03
    కు
    1.02
    اکي
    1.02
    POSITIVE LOGITS
    x
    1.66
    i
    1.61
    ra
    1.30
    al
    1.24
    j
    1.19
    that
    1.17
    f
    1.16
    ,
    1.16
    z
    1.16
    ne
    1.14
    Activations Density 0.002%

    No Known Activations