© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111893
    Prev
    Next
    INDEX
    Explanations

    Polish verb 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_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
    .
    1.37
    ።
    1.30
    是
    1.27
    는
    1.09
     في
    1.06
     pressão
    0.99
     in
    0.98
    是对
    0.98
    は
    0.98
    ۔
    0.96
    POSITIVE LOGITS
    u
    1.74
    v
    1.35
    انی
    1.34
    تی
    1.18
    ’
    1.11
    و
    1.07
    ลูกค้า
    1.06
     or
    1.05
    ל
    1.05
    nent
    1.02
    Activations Density 0.000%

    No Known Activations