© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9721
    Prev
    Next
    INDEX
    Explanations

    log

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    명이
    0.72
    毓
    0.67
    명
    0.61
     openly
    0.61
     உப
    0.60
     ogl
    0.60
     eccles
    0.60
    ន្ត
    0.60
     सला
    0.60
     Chapel
    0.59
    POSITIVE LOGITS
     رم
    0.75
    iors
    0.72
    ாய்ச்ச
    0.71
    iori
    0.71
     râ
    0.70
    тего
    0.69
    ₁.
    0.68
    роид
    0.67
    arp
    0.66
     во
    0.66
    Activations Density 0.001%

    No Known Activations