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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2866
    Prev
    Next
    INDEX
    Explanations

    online services and platforms

    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
    fico
    0.85
     кстати
    0.85
    $',
    0.85
     deth
    0.83
     Rxd
    0.83
    {(
    0.82
    (\{
    0.82
    𝗳
    0.82
     polynomials
    0.81
    reo
    0.80
    POSITIVE LOGITS
    uvat
    0.90
    ви
    0.87
    ิน
    0.85
    ดิจ
    0.85
     lalu
    0.84
     siebie
    0.84
    রাদ
    0.81
     apothe
    0.80
    сць
    0.80
    م
    0.79
    Activations Density 0.159%

    No Known Activations