© 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. 53576
    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
    eda
    0.39
    ibb
    0.38
     hesitated
    0.38
     खींच
    0.38
     hesitate
    0.37
     ફૂ
    0.36
     yazd
    0.36
    敢
    0.36
    侈
    0.36
     copie
    0.35
    POSITIVE LOGITS
    でもある
    0.38
    んにちは
    0.38
    ,*/}*.
    0.37
    しない
    0.36
     Bowie
    0.36
     Tages
    0.35
     magasins
    0.35
     സാഹചര്യ
    0.35
     cities
    0.34
     soli
    0.34
    Activations Density 0.000%

    No Known Activations