© 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. 6958
    Prev
    Next
    INDEX
    Explanations

    html lang="

    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
    х
    2.97
    ين
    2.63
     Sejam
    2.36
    िन
    2.31
    ല്ലാം
    2.23
     Essa
    2.21
    =\{\
    2.20
    𝑃
    2.18
    |".
    2.17
     faptul
    2.17
    POSITIVE LOGITS
    ه
    3.03
    o
    2.91
    mathbb
    2.89
    ्ज
    2.81
    شان
    2.73
    soever
    2.70
    هَا
    2.69
    liang
    2.61
    EM
    2.57
    udges
    2.57
    Activations Density 0.001%

    No Known Activations