© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214489
    Prev
    Next
    INDEX
    Explanations

    Arabic words related to days/common nouns

    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_5_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
    ר
    0.95
    he
    0.92
     receivable
    0.91
     изготов
    0.86
    न्दावन
    0.86
    м
    0.86
    hav
    0.86
     странице
    0.86
    heh
    0.86
    를
    0.86
    POSITIVE LOGITS
    지
    1.40
    리
    1.25
    ك
    1.16
    Après
    1.12
    ită
    1.11
    كار
    1.08
    ق
    1.07
    дят
    1.06
     to
    1.02
    -
    1.02
    Activations Density 0.000%

    No Known Activations