© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210749
    Prev
    Next
    INDEX
    Explanations

    translation services

    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_20_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
    碉
    0.41
     abbrevi
    0.40
     Molecule
    0.40
     pedestrian
    0.39
     Armor
    0.39
     molecule
    0.38
     armor
    0.38
     athe
    0.37
    촬영
    0.36
     {
    0.36
    POSITIVE LOGITS
     निरीक्षण
    0.45
    yyyy
    0.44
     देनी
    0.44
    blk
    0.43
    clu
    0.42
     riguard
    0.42
     चार्ट
    0.42
    cluding
    0.42
     بخ
    0.42
    reaching
    0.41
    Activations Density 0.000%

    No Known Activations