© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11389
    Prev
    Next
    INDEX
    Explanations

    React React.FC and Plugin

    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_40_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
     Buj
    0.46
     ประมาณ
    0.42
     encuentros
    0.40
    ))+\
    0.40
     DENUMIRE
    0.39
    SubSystem
    0.39
    ႄ
    0.39
    遇
    0.39
     Radeon
    0.38
     MDET
    0.38
    POSITIVE LOGITS
    jima
    0.40
    **/
    0.36
     C
    0.35
    Full
    0.35
     Vers
    0.35
    浏览
    0.35
     amplified
    0.35
     До
    0.34
     finals
    0.34
     Purchases
    0.34
    Activations Density 0.001%

    No Known Activations