© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32160
    Prev
    Next
    INDEX
    Explanations

    `pip install` python

    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
     be
    1.41
    3
    1.12
     in
    1.10
     are
    1.00
     mondo
    1.00
     van
    0.97
    4
    0.97
     la
    0.96
    5
    0.96
     σε
    0.95
    POSITIVE LOGITS
    ↵↵
    0.99
    д
    0.91
    quela
    0.73
     Wasn
    0.68
     That
    0.66
    درا
    0.65
    a
    0.65
    ре
    0.64
     They
    0.64
    DVRIP
    0.63
    Activations Density 0.009%

    No Known Activations