© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1355
    Prev
    Next
    INDEX
    Explanations

    you believe

    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_39_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
     contractile
    0.39
    omitem
    0.39
     वस्तुओं
    0.39
    omponent
    0.38
    땄
    0.38
     DeepCollection
    0.37
    icked
    0.36
     potom
    0.36
     використовувати
    0.36
     otten
    0.36
    POSITIVE LOGITS
     $[-
    0.41
     Bootstrap
    0.38
     Bosch
    0.37
     Sinclair
    0.36
    бора
    0.36
     LX
    0.36
     Apple
    0.36
    pts
    0.36
     !!
    0.35
     RY
    0.35
    Activations Density 0.001%

    No Known Activations