© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207194
    Prev
    Next
    INDEX
    Explanations

    subprocess stdout PIPE

    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_19_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
    -
    0.50
     wand
    0.48
     malu
    0.47
     mal
    0.45
    ー
    0.45
     wink
    0.43
    ми
    0.42
     aquarium
    0.41
    ся
    0.41
    м
    0.41
    POSITIVE LOGITS
     bottlenecks
    0.59
     Вме
    0.52
    தமிழக
    0.51
     Mahmood
    0.50
     Patterson
    0.50
    ધાનસભા
    0.50
    荩
    0.49
     Kenney
    0.49
    okovic
    0.48
     Retrieves
    0.48
    Activations Density 0.000%

    No Known Activations