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. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 14881
    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
     Вот
    0.66
    elta
    0.65
    →</
    0.64
    сюда
    0.64
    шек
    0.64
     else
    0.64
     ofstream
    0.62
    igue
    0.62
    ellik
    0.62
    },-
    0.61
    POSITIVE LOGITS
    溏
    0.67
    GEN
    0.67
    ANC
    0.65
    צא
    0.65
    નગર
    0.64
    ปฏิบัติ
    0.64
     nghiên
    0.63
    వచ్చు
    0.61
     照明
    0.61
     appréci
    0.61
    Activations Density 0.085%

    No Known Activations