© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45494
    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_10_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
     purifier
    0.47
    ן
    0.47
     masak
    0.47
    para
    0.46
    ى
    0.45
    <unused78>
    0.44
    sten
    0.43
    param
    0.43
     har
    0.43
     rôle
    0.43
    POSITIVE LOGITS
    াকি
    0.49
    autical
    0.47
     Εκ
    0.46
    춧
    0.46
     Konz
    0.44
    aglio
    0.44
    ologii
    0.44
     MLAs
    0.43
     오래
    0.43
    불어
    0.43
    Activations Density 0.000%

    No Known Activations