© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145286
    Prev
    Next
    INDEX
    Explanations

    Arabic "in", foreign scripts, programming events

    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_0_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
    ل
    1.56
    리
    1.55
    बी
    1.54
    मा
    1.48
    ва
    1.44
    લ
    1.36
    ला
    1.34
    ル
    1.23
    ב
    1.20
    ?
    1.19
    POSITIVE LOGITS
    ா
    1.23
    ا
    1.20
     في
    1.19
     выпол
    1.10
    在
    1.10
    于
    1.06
    ি
    1.02
    다
    1.02
    ក្នុង
    1.01
    𝙖
    1.01
    Activations Density 0.000%

    No Known Activations