Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 9454
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_31_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
     गरम
    0.66
     đại
    0.65
    Вер
    0.62
     सु
    0.62
     চাচ
    0.61
     थकान
    0.61
     ਕਰਨ
    0.61
    誒
    0.60
     ज्वाइन
    0.60
    ਅ
    0.59
    POSITIVE LOGITS
     nargs
    0.68
     gest
    0.65
     Ell
    0.64
    oy
    0.60
    iless
    0.58
    urne
    0.58
    ural
    0.58
    arette
    0.57
     situe
    0.56
    ello
    0.56
    Activations Density 0.000%

    No Known Activations