© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5452
    Prev
    Next
    INDEX
    Explanations

    United Arab Emirates

    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_3_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
    ва
    2.31
    €™
    2.31
     ď
    2.30
     humble
    2.27
    {
    2.27
     {:?}",
    2.22
     chances
    2.16
     luck
    2.15
    вані
    2.13
     Vậy
    2.12
    POSITIVE LOGITS
    त
    2.71
    वय
    2.52
    з
    2.41
     énergétique
    2.38
    zeitig
    2.37
    য়েছে
    2.35
    तला
    2.33
    Bought
    2.30
    то
    2.29
     panahon
    2.29
    Activations Density 0.017%

    No Known Activations