© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258903
    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_22_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
     threatened
    0.54
     unemployed
    0.49
     threaten
    0.49
    다
    0.49
     free
    0.47
     crist
    0.47
     ghost
    0.47
     {
    0.46
    threat
    0.44
     blood
    0.44
    POSITIVE LOGITS
     切
    0.55
    軟件
    0.51
     المُ
    0.50
     କରି
    0.48
     sintomi
    0.47
    omi
    0.47
     lateribus
    0.47
     洗
    0.46
     एक्सच
    0.46
     сторона
    0.46
    Activations Density 0.000%

    No Known Activations