© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194329
    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_9_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
     China
    0.59
     Staphylococcus
    0.56
     Houston
    0.54
     Leicester
    0.53
     李
    0.53
     José
    0.53
     Mo
    0.52
     Tam
    0.52
     Dick
    0.52
     Leonardo
    0.52
    POSITIVE LOGITS
     водой
    0.50
    الغ
    0.50
    Participant
    0.49
    Brom
    0.49
    િ
    0.49
    ᠩ
    0.49
    OVER
    0.48
    unpack
    0.48
    Packed
    0.48
    Experiment
    0.48
    Activations Density 0.000%

    No Known Activations