© 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. 6499
    Prev
    Next
    INDEX
    Explanations

    coming out

    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
    س
    2.96
    ה
    2.22
    с
    2.15
    хи
    2.15
    ीजन
    2.14
     instalments
    2.13
    на
    2.03
    ن
    2.01
    imeters
    2.00
    ು
    1.98
    POSITIVE LOGITS
    dan
    2.57
    ตรฐาน
    2.53
    daki
    2.40
    dies
    2.21
    dir
    2.19
    dı
    2.17
    da
    2.15
     eben
    2.11
    dish
    2.07
    dent
    2.05
    Activations Density 0.023%

    No Known Activations