© 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. 35096
    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
    醝
    0.38
     interested
    0.35
    酛
    0.35
     لوی
    0.35
     interesa
    0.35
    小学校
    0.34
    ్రె
    0.34
    HTTPRequest
    0.34
    䣷
    0.33
     doe
    0.33
    POSITIVE LOGITS
    DSC
    0.38
    accident
    0.37
    Keeping
    0.37
    Headers
    0.36
     obsc
    0.36
     사고
    0.35
     CONTRIBUTION
    0.35
    Eve
    0.34
     Keeping
    0.34
    WL
    0.34
    Activations Density 0.000%

    No Known Activations