© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20580
    Prev
    Next
    INDEX
    Explanations

    away from

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    由
    3.13
     由
    2.61
    是由
    1.97
     oleh
    1.56
     توسط
    1.54
    โดย
    1.21
     بواسطة
    1.20
     by
    1.12
    oleh
    0.94
    ໂດຍ
    0.92
    POSITIVE LOGITS
     ממש
    1.11
     off
    0.47
     away
    0.44
     maad
    0.39
    away
    0.36
     equilibrium
    0.35
    ฏ
    0.34
    闓
    0.34
     magas
    0.34
    समाचार
    0.34
    Activations Density 0.061%

    No Known Activations