© 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. 8178
    Prev
    Next
    INDEX
    Explanations

    headings containing website titles

    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
    紝
    1.90
    년대
    1.86
     teat
    1.55
    吒
    1.53
     linéaire
    1.51
    Цент
    1.49
    И
    1.48
     cun
    1.45
     aver
    1.42
    යෙන්
    1.41
    POSITIVE LOGITS
    拡散方程式
    1.61
    stuff
    1.56
     міста
    1.53
    ه
    1.52
    🏼
    1.48
    lw
    1.48
    🏽
    1.48
    🏿
    1.45
     misspelled
    1.44
    Charg
    1.44
    Activations Density 0.002%

    No Known Activations