© 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. 6418
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ことにより
    1.98
    ം
    1.95
    こと
    1.93
    窣
    1.90
    মা
    1.80
    schluss
    1.78
    ка
    1.72
    ся
    1.72
    いない
    1.67
    НИ
    1.66
    POSITIVE LOGITS
    or
    1.83
     pois
    1.76
    其
    1.75
     laut
    1.75
    𝓼
    1.63
     посла
    1.60
     बातों
    1.60
    enment
    1.59
     sm
    1.54
     khấu
    1.53
    Activations Density 0.183%

    No Known Activations