© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7568
    Prev
    Next
    INDEX
    Explanations

    Dense layer in code or Desk Support

    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
    ن
    0.81
    ح
    0.80
    на
    0.80
    it
    0.79
    (\
    0.77
    紝
    0.75
    𝖘
    0.71
    لل
    0.71
    ઉન
    0.70
    fer
    0.69
    POSITIVE LOGITS
    ことができる
    0.93
    എം
    0.85
     conspicuously
    0.84
    тино
    0.80
    必要がある
    0.79
     frosting
    0.79
    EntryPoint
    0.79
     отличаются
    0.78
    MenuStrip
    0.77
    氲
    0.77
    Activations Density 0.002%

    No Known Activations