© 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. 242264
    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
     зем
    0.48
    ностях
    0.40
    谌
    0.38
    third
    0.38
    searchview
    0.37
    Scandinavian
    0.37
    Bedroom
    0.36
    ৯
    0.36
    زمین
    0.36
     ஆல
    0.35
    POSITIVE LOGITS
     eth
    0.41
    webElementXpaths
    0.38
    бавля
    0.36
     Paxton
    0.36
    प्रधान
    0.35
     টেক
    0.35
    headless
    0.35
     විය
    0.35
    artz
    0.35
    havior
    0.35
    Activations Density 0.000%

    No Known Activations