© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241960
    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_40_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
     επισ
    0.41
    めます
    0.41
    終
    0.40
    Sci
    0.38
    CrossRef
    0.38
    Rear
    0.37
    终
    0.37
    jenje
    0.37
    hbs
    0.36
    Side
    0.36
    POSITIVE LOGITS
     व्यक्ति
    0.39
    ꒷
    0.38
    izam
    0.36
     bananas
    0.36
    ipine
    0.36
     place
    0.35
     đất
    0.35
     blueberries
    0.35
     componentDid
    0.35
     gly
    0.34
    Activations Density 0.000%

    No Known Activations