© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3715
    Prev
    Next
    INDEX
    Explanations

    django.contrib.auth and models

    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
     thorough
    1.62
    m
    1.56
    den
    1.53
    t
    1.51
    тың
    1.46
    theo
    1.44
    Departure
    1.42
    ti
    1.42
    \/
    1.41
    ها
    1.40
    POSITIVE LOGITS
     biggest
    1.53
    ו
    1.50
     muita
    1.44
    是因为
    1.40
    o
    1.38
     jaga
    1.37
     envol
    1.36
    ेंसिल
    1.36
     probs
    1.35
    ه
    1.34
    Activations Density 0.001%

    No Known Activations