© 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. 205706
    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
    瓶
    0.48
    лож
    0.47
    㫣
    0.46
    gateTime
    0.45
    Sole
    0.44
    ্যাল
    0.44
     Alignment
    0.44
    趄
    0.44
    Motivation
    0.43
    Otp
    0.43
    POSITIVE LOGITS
    м
    0.61
     escaped
    0.54
     prayed
    0.54
    ,
    0.54
    ުގައި
    0.52
     dismissed
    0.51
     pored
    0.50
     pondered
    0.50
     doa
    0.49
     chiam
    0.49
    Activations Density 0.000%

    No Known Activations