© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 2950
    Prev
    Next
    INDEX
    Explanations

    Anti-Defamation League

    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_5_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
    ভাসের
    0.68
    वायरस
    0.68
     lapply
    0.67
    ות
    0.65
    좇
    0.65
    tic
    0.63
    ंग्रेस
    0.63
    ം
    0.63
    的网络
    0.62
    т
    0.62
    POSITIVE LOGITS
     festive
    0.68
     ease
    0.67
     Festive
    0.65
    цы
    0.65
    acé
    0.64
     دې
    0.64
     aches
    0.64
    haran
    0.64
    supporting
    0.63
    startY
    0.63
    Activations Density 0.001%

    No Known Activations