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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15021
    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_19_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
    邸
    0.75
    !(
    0.72
    。(
    0.71
     skj
    0.69
     conservatively
    0.68
     permanently
    0.68
     seseorang
    0.68
    ீர்
    0.68
     :(
    0.67
    ELD
    0.67
    POSITIVE LOGITS
    Imagem
    0.66
    icio
    0.63
    imoto
    0.63
    ancı
    0.63
    او
    0.63
    oriale
    0.62
     ഉ
    0.61
    verters
    0.61
     Ciò
    0.61
    dance
    0.61
    Activations Density 0.000%

    No Known Activations