© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222700
    Prev
    Next
    INDEX
    Explanations

    internet and downloads

    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_10_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
    阈
    0.55
    စိတ်
    0.53
     څرنګوالی
    0.52
     တယ်
    0.51
    တွင်
    0.50
     Andreev
    0.50
    အစိတ်အပိုင်း
    0.50
     ဗ
    0.50
     Maki
    0.50
     შესახებ
    0.49
    POSITIVE LOGITS
    I
    0.61
    K
    0.53
    ون
    0.50
    U
    0.50
    in
    0.48
    ни
    0.47
    os
    0.47
    OS
    0.47
    ET
    0.46
    he
    0.46
    Activations Density 0.000%

    No Known Activations