© 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. 80980
    Prev
    Next
    INDEX
    Explanations

    hypostatic, homeostatic, allostatic, pseudostatic, orthostatic, hemostatic, magnetostatic

    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
    '
    2.20
    ي
    2.09
    ون
    1.82
    ก
    1.74
    ت
    1.70
    <0x80>
    1.70
    تي
    1.65
    يي
    1.61
    ט
    1.53
    ס
    1.52
    POSITIVE LOGITS
     a
    1.16
    os
    1.14
    3
    1.12
    d
    1.09
     ने
    1.08
    ありません
    1.06
    。.
    1.04
     आहे
    1.00
     kaleidoscopic
    0.98
    ų
    0.98
    Activations Density 0.001%

    No Known Activations