© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143039
    Prev
    Next
    INDEX
    Explanations

    planes and deplaning

    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
    可以
    1.16
    ní
    1.14
    鐒
    1.14
    用於
    1.10
    '
    1.10
    ním
    1.09
    用
    1.08
    ंकन
    1.05
     Geißler
    1.05
    zetten
    1.05
    POSITIVE LOGITS
    a
    2.53
    지
    2.14
    ה
    2.00
    י
    1.97
    ه
    1.87
    ק
    1.86
    া
    1.84
    ล
    1.77
    л
    1.75
    า
    1.72
    Activations Density 0.000%

    No Known Activations