© 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. 2930
    Prev
    Next
    INDEX
    Explanations

    the most / first / largest

    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
     somehow
    1.06
    removeAttr
    1.05
    Shirts
    1.00
    𝐑
    0.99
    ك
    0.96
    जूद
    0.95
     prominently
    0.94
    本発明
    0.92
    groomed
    0.89
    చేసిన
    0.88
    POSITIVE LOGITS
    elif
    0.82
    }^{
    0.78
    ур
    0.75
    ="#"
    0.75
    蝓
    0.75
    ีก
    0.74
    नेटरी
    0.74
    
    0.74
    াম
    0.74
    eah
    0.74
    Activations Density 0.006%

    No Known Activations