© 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. 143990
    Prev
    Next
    INDEX
    Explanations

    ITS AT

    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
    س
    1.25
    you
    1.23
    lla
    1.20
     قاسمی
    1.17
    y
    1.16
    den
    1.15
    ri
    1.14
    SXml
    1.13
    OLE
    1.13
    yana
    1.12
    POSITIVE LOGITS
    л
    2.31
    ل
    2.30
    ة
    2.28
    ك
    1.70
    ing
    1.69
    ات
    1.64
    ية
    1.45
    ↵↵
    1.38
    ル
    1.35
    er
    1.34
    Activations Density 0.001%

    No Known Activations