© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102663
    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_44_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
     faktor
    0.38
    Owin
    0.38
    Inspect
    0.37
    秋
    0.37
    Factors
    0.36
     PSE
    0.36
     ACTUAL
    0.36
     चिकित्स
    0.36
     रहीम
    0.35
    ịch
    0.35
    POSITIVE LOGITS
     halt
    0.41
     halts
    0.39
    夸
    0.38
     ek
    0.38
     Ek
    0.38
    εκ
    0.38
     केंद्रीय
    0.38
     hologram
    0.38
     dropout
    0.37
     get
    0.36
    Activations Density 0.000%

    No Known Activations