© 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. 6535
    Prev
    Next
    INDEX
    Explanations

    might be

    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
    べき
    0.73
    collation
    0.68
     woe
    0.66
    ০
    0.65
    ize
    0.63
    ことから
    0.59
    িন
    0.58
     διάρκεια
    0.57
    ట్ట
    0.57
    or
    0.56
    POSITIVE LOGITS
    𝒈
    0.68
    س
    0.66
    ινων
    0.66
    hibition
    0.63
    hn
    0.63
    यों
    0.62
    Acknowled
    0.61
    ва
    0.60
    বা
    0.59
    ت
    0.59
    Activations Density 0.128%

    No Known Activations