© 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. 199304
    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
    ok
    0.54
    อบ
    0.51
    og
    0.50
    ak
    0.48
    คำ
    0.47
     เข้า
    0.46
    ry
    0.46
    I
    0.46
    ú
    0.46
    後
    0.46
    POSITIVE LOGITS
     нацыяна
    0.52
    cieron
    0.50
    Cntr
    0.49
    cnico
    0.48
    ლებელია
    0.48
    ચ્છ
    0.48
    لوار
    0.48
     Valletta
    0.48
     patitth
    0.47
     uniformed
    0.47
    Activations Density 0.000%

    No Known Activations