© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18251
    Prev
    Next
    INDEX
    Explanations

    sub-tasks

    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_34_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
    damaged
    0.39
    ய்ய
    0.37
    different
    0.36
    drying
    0.36
     ಪದ
    0.36
    ilerine
    0.35
    ädchen
    0.35
    袁
    0.35
    getY
    0.35
    KJ
    0.34
    POSITIVE LOGITS
     *@
    0.43
     ->
    0.39
     Rent
    0.38
     फ्लिप
    0.38
     "<<
    0.38
    是我
    0.37
     communication
    0.37
     **
    0.37
     %(
    0.37
     nog
    0.36
    Activations Density 0.035%

    No Known Activations