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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6694
    Prev
    Next
    INDEX
    Explanations

    NVIDIA GPU series VRAM

    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
    ب
    4.19
    ン
    3.47
    at
    3.38
    л
    3.20
    त
    3.14
    ন
    2.96
    на
    2.83
    ব
    2.81
    
    2.79
    नियर
    2.77
    POSITIVE LOGITS
    |\
    2.85
    ѕ
    2.81
     startIndex
    2.49
    ेक्ट
    2.48
    𝙚
    2.42
    і
    2.40
     whence
    2.32
     statically
    2.29
     shun
    2.26
    iculo
    2.21
    Activations Density 0.142%

    No Known Activations