© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174078
    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_20_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
     (
    0.56
     black
    0.49
     loop
    0.47
     _
    0.47
    ه
    0.47
     umbrella
    0.46
     count
    0.46
     ruling
    0.45
     blood
    0.45
     rule
    0.44
    POSITIVE LOGITS
    Sexy
    0.46
    andled
    0.45
    不安
    0.44
    )$,
    0.43
    бою
    0.43
    くなります
    0.42
    差別
    0.42
     samtid
    0.42
    žiť
    0.42
    xiety
    0.41
    Activations Density 0.000%

    No Known Activations