© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 86794
    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_23_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
    clan
    0.45
    מק
    0.44
     rifer
    0.43
    MBOL
    0.43
    Sign
    0.42
     appr
    0.42
    Signs
    0.41
    ת
    0.41
    Lear
    0.40
     Học
    0.40
    POSITIVE LOGITS
    ौली
    0.45
     ട
    0.43
     যের
    0.41
     業務用
    0.39
     woods
    0.39
    겠지만
    0.38
    instrList
    0.38
     wygl
    0.37
     मातृ
    0.37
     javac
    0.37
    Activations Density 0.000%

    No Known Activations