© 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. 161512
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    و
    1.17
    ia
    1.13
    ا
    1.02
    다
    1.00
    ू
    0.99
    ן
    0.99
    ua
    0.99
    ê
    0.96
    ë
    0.96
    ı
    0.95
    POSITIVE LOGITS
    h
    1.53
    ли
    1.27
    er
    1.21
    ر
    1.21
    Lors
    1.18
    ிய
    1.16
     działa
    1.15
    iş
    1.13
    ча
    1.12
     inconn
    1.11
    Activations Density 0.002%

    No Known Activations