© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197382
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
    aws
    0.48
     rebounded
    0.48
    ガラス
    0.46
     responsabilità
    0.46
    ೀಯ
    0.45
    覺
    0.44
    mz
    0.44
    সাহিত্য
    0.44
    𒍪
    0.44
    โย
    0.43
    POSITIVE LOGITS
     men
    0.51
    мени
    0.51
     Men
    0.51
     Organize
    0.47
    inak
    0.44
     Promise
    0.44
    స్
    0.44
     Kell
    0.43
    وة
    0.42
     Mint
    0.42
    Activations Density 0.000%

    No Known Activations