© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9059
    Prev
    Next
    INDEX
    Explanations

    try

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     swoim
    0.71
     tranquila
    0.70
     geboren
    0.68
    ச்சா
    0.66
     জে
    0.64
     standaard
    0.64
     Comun
    0.64
    ؤ
    0.64
    ཉ
    0.64
     Orig
    0.64
    POSITIVE LOGITS
     concentration
    0.67
    <0xA2>
    0.67
    comodule
    0.64
     buccal
    0.64
    itosan
    0.64
    ihat
    0.63
    (#
    0.62
     Scotland
    0.62
    귿
    0.62
     спро
    0.61
    Activations Density 0.000%

    No Known Activations