© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75261
    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_31_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
    сора
    0.38
    ActionsCallback
    0.36
    personen
    0.36
    ః
    0.36
    nehmer
    0.36
     वस्तु
    0.35
    ्व
    0.35
     সদস্যরা
    0.35
     বস্ত
    0.34
    aila
    0.34
    POSITIVE LOGITS
    Something
    0.40
    APPROVED
    0.38
    懂
    0.36
     احد
    0.35
    ATTACH
    0.35
     রাকাত
    0.34
    LI
    0.34
    ammam
    0.34
    Okay
    0.33
    Highest
    0.33
    Activations Density 0.000%

    No Known Activations