© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110466
    Prev
    Next
    INDEX
    Explanations

    JD, Job Description, JD.com, JDG, JD1, JD

    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
    '
    1.51
    ۰
    1.32
    0
    1.30
    ৫
    1.25
    ០
    1.17
    ၀
    1.16
    ר
    1.14
    تهم
    1.12
    تان
    1.10
    ↵
    1.08
    POSITIVE LOGITS
    ك
    2.09
    на
    1.91
    ری
    1.88
    ला
    1.80
    ма
    1.62
    ку
    1.59
    ра
    1.52
    ני
    1.52
    ре
    1.50
     ότι
    1.44
    Activations Density 0.001%

    No Known Activations