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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261442
    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_10_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
    로
    1.22
     суда
    1.06
     суд
    1.02
     jäl
    0.99
    дт
    0.92
    相互
    0.91
    ిన
    0.89
                   
    0.89
    𝗋
    0.89
     проце
    0.89
    POSITIVE LOGITS
    bumptech
    1.37
    ៌
    1.29
    ژی
    1.27
     gial
    1.23
     velvety
    1.23
    salmon
    1.22
     fluxes
    1.21
    t
    1.21
     masculina
    1.20
     parmes
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.