© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15840
    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_40_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
     poisons
    0.41
    Plain
    0.41
    ੴ
    0.40
     plain
    0.38
     პ
    0.38
     plo
    0.38
     poison
    0.38
     henry
    0.37
     ገ
    0.37
     Plain
    0.37
    POSITIVE LOGITS
    production
    0.42
    生产
    0.38
     concentración
    0.38
    concentration
    0.37
     indefinite
    0.36
     concent
    0.36
     concentra
    0.36
     скон
    0.35
     décrire
    0.35
    probe
    0.35
    Activations Density 0.000%

    No Known Activations