© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168435
    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_34_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
    െടുത്ത
    0.39
     supporter
    0.38
    лору
    0.35
    ।''
    0.35
    㣻
    0.34
    惴
    0.34
    ।’’
    0.34
    льну
    0.34
    shut
    0.34
     arach
    0.33
    POSITIVE LOGITS
     تس
    0.42
    츠
    0.40
    Fault
    0.40
    overflow
    0.40
     overflows
    0.39
    溢
    0.39
    Rocks
    0.38
     verw
    0.38
    Animating
    0.37
     Rocks
    0.37
    Activations Density 0.000%

    No Known Activations