© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8226
    Prev
    Next
    INDEX
    Explanations

    variable attributes and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    क
    1.22
    व
    1.08
    े
    1.05
    ו
    1.02
    तः
    1.00
    ك
    0.97
    ant
    0.96
    ें
    0.96
    ત
    0.94
    ᱽ
    0.92
    POSITIVE LOGITS
     facendo
    1.02
    जनबी
    0.97
     amplo
    0.97
     препара
    0.97
     Wörter
    0.95
     orden
    0.94
    ции
    0.93
     creo
    0.93
     течение
    0.92
     obat
    0.92
    Activations Density 0.092%

    No Known Activations