© 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
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3421
    Prev
    Next
    INDEX
    Explanations

    rock paper scissors

    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
    odenal
    0.48
     তোলে
    0.48
     πως
    0.46
    त
    0.46
     kneeling
    0.45
    ipped
    0.45
    auty
    0.44
    srv
    0.44
    resso
    0.44
     flown
    0.43
    POSITIVE LOGITS
    ع
    0.56
    간
    0.54
    즈
    0.53
     folate
    0.50
    су
    0.50
    მ
    0.50
    ер
    0.48
    то
    0.47
    س
    0.46
     добав
    0.46
    Activations Density 0.137%

    No Known Activations