© 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. 44712
    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
    marketing
    0.47
     playing
    0.46
    一流
    0.45
    、
    0.44
     paraly
    0.43
     must
    0.43
     müssen
    0.42
    playing
    0.41
     outbreak
    0.40
     credible
    0.40
    POSITIVE LOGITS
    깥
    0.54
    FixedHeight
    0.54
     TouchUtils
    0.54
    𝟖
    0.53
    ERICK
    0.51
     일반
    0.49
    OneFrame
    0.49
    埓
    0.49
    စျေး
    0.48
    संख्य
    0.48
    Activations Density 0.000%

    No Known Activations