© 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. 109679
    Prev
    Next
    INDEX
    Explanations

    verl, verzweifelt, verkauf, veränderlichkeit

    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
    ل
    1.63
    트
    1.48
    л
    1.47
    ,
    1.40
    ल
    1.35
    ル
    1.33
    지
    1.30
    ر
    1.27
    ز
    1.25
    '
    1.24
    POSITIVE LOGITS
     for
    1.58
     in
    1.46
     It
    1.36
     at
    1.24
     from
    1.22
    1
    1.17
    لي
    1.09
     to
    1.06
     of
    1.05
     on
    1.05
    Activations Density 0.000%

    No Known Activations