© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 144570
    Prev
    Next
    INDEX
    Explanations

    distinguishing Features or Cases

    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
    ın
    1.38
    ме
    1.36
    ре
    1.27
    <0xBE>
    1.23
    و
    1.23
    的我
    1.20
    的区别
    1.17
    <0x80>
    1.13
     I
    1.13
    ْ
    1.13
    POSITIVE LOGITS
    ם
    2.16
    ด
    1.77
    า
    1.76
    ла
    1.75
    د
    1.68
    י
    1.66
    in
    1.63
    দ
    1.53
    ט
    1.47
    i
    1.44
    Activations Density 0.000%

    No Known Activations