© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240204
    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_25_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
     isotropy
    0.37
     Roshelle
    0.36
     مقاوم
    0.35
     നെറ്റ്‌വർ
    0.35
     isotropic
    0.34
     anisotropy
    0.34
    }$&$-
    0.34
     webbrowser
    0.33
     vesting
    0.33
    ബ്‌
    0.33
    POSITIVE LOGITS
     oficialmente
    0.41
    asInstanceOf
    0.41
     besten
    0.40
    osts
    0.39
    iew
    0.39
     増
    0.39
     postings
    0.39
    iete
    0.39
    oa
    0.38
    adoria
    0.38
    Activations Density 0.000%

    No Known Activations