© 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-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32408
    Prev
    Next
    INDEX
    Explanations

    RxJS and Rx terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    5
    0.37
    6
    0.36
    0
    0.34
    7
    0.30
    8
    0.29
    9
    0.28
    4
    0.27
    1
    0.26
    ים
    0.25
    <0x0D>
    0.24
    POSITIVE LOGITS
    m
    0.26
    ן
    0.22
    as
    0.19
    os
    0.19
    panelMenuList
    0.19
     বিচার
    0.19
     ዋ
    0.19
    p
    0.18
    <0x89>
    0.18
    rishna
    0.18
    Activations Density 0.002%

    No Known Activations