© 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. 221179
    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
    back
    0.61
    ين
    0.57
     Гуляць
    0.57
    igene
    0.51
    ра
    0.50
     Благодаря
    0.50
    wane
    0.50
    }$.
    0.49
    aring
    0.49
     embry
    0.49
    POSITIVE LOGITS
     Hitch
    0.49
    我国
    0.44
    以来
    0.43
    たと
    0.43
     Cue
    0.42
     Mechan
    0.42
    ئین
    0.42
    国家
    0.42
    讲述
    0.42
    そば
    0.42
    Activations Density 0.000%

    No Known Activations