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. 4091
    Prev
    Next
    INDEX
    Explanations

    in the end

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    اتها
    1.93
    اته
    1.80
    ات
    1.72
    $('#
    1.71
    环境下
    1.65
    рое
    1.63
    ভাবে
    1.62
    orious
    1.61
    xious
    1.60
    ishly
    1.59
    POSITIVE LOGITS
    ძ
    1.79
    Czas
    1.63
     contas
    1.60
     kuitenkin
    1.57
     laat
    1.55
    ച്ച
    1.54
     allemaal
    1.53
     déb
    1.51
     Durch
    1.49
     siècles
    1.48
    Activations Density 0.000%

    No Known Activations