© 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. 157457
    Prev
    Next
    INDEX
    Explanations

    Arabic and Urdu characters and transliterations

    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
    ні
    1.43
    2
    1.36
    de
    1.13
    jährige
    1.12
    0
    1.10
    َة
    1.04
    ỡng
    1.01
    dimensional
    1.00
    line
    1.00
    gan
    0.98
    POSITIVE LOGITS
    د
    1.33
    জ
    1.16
    い
    1.15
    д
    1.13
     THAT
    1.07
    લ
    1.06
    드
    1.06
     zabaw
    1.04
     monstros
    1.02
    ↵
    1.02
    Activations Density 0.002%

    No Known Activations