© 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. 82710
    Prev
    Next
    INDEX
    Explanations

    names and foreign 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_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
    し
    1.40
    d
    1.38
    ки
    1.36
    も
    1.36
    入力
    1.30
    もら
    1.30
    ご
    1.27
    使用
    1.26
    使う
    1.25
    ب
    1.24
    POSITIVE LOGITS
    ing
    1.70
    ة
    1.54
    ния
    1.48
    il
    1.48
    ur
    1.32
    ва
    1.32
    ות
    1.30
    that
    1.28
     scrutin
    1.21
    л
    1.21
    Activations Density 0.000%

    No Known Activations