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. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4472
    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_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
    ी
    0.36
     привле
    0.36
     PDT
    0.34
    WCHAR
    0.32
    없이
    0.32
    Uart
    0.31
    RNN
    0.31
     peine
    0.31
     wobble
    0.31
     relegation
    0.31
    POSITIVE LOGITS
    س
    0.47
    ச
    0.45
    സ
    0.41
    ج
    0.41
     soggiorno
    0.39
    warl
    0.39
    स
    0.38
    гова
    0.38
    ન્દ્ર
    0.38
    já
    0.37
    Activations Density 0.124%

    No Known Activations