© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35428
    Prev
    Next
    INDEX
    Explanations

    condensate

    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_7_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
    ä
    0.56
    $
    0.52
    the
    0.51
    ā
    0.47
    t
    0.47
     It
    0.46
    ні
    0.43
    h
    0.43
    rik
    0.42
    ö
    0.42
    POSITIVE LOGITS
     הר
    0.51
     airbags
    0.49
     ப
    0.48
     وش
    0.48
     amu
    0.48
     Ад
    0.48
     التق
    0.48
     legumes
    0.46
     ا
    0.46
     Agregar
    0.46
    Activations Density 0.010%

    No Known Activations