© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54153
    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_30_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
     afforded
    0.39
    icularly
    0.39
     ገ
    0.37
     captivity
    0.34
    níky
    0.34
    ീകരണ
    0.34
    BSData
    0.34
    setWindowTitle
    0.34
    𝔯
    0.34
    囔
    0.34
    POSITIVE LOGITS
     JLabel
    0.38
     упа
    0.36
     összes
    0.33
    錦
    0.33
    คิด
    0.33
    Ī
    0.33
    igr
    0.33
     ín
    0.33
    leftharpoons
    0.33
     Chir
    0.32
    Activations Density 0.000%

    No Known Activations