© 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. 244321
    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
    𝐔
    0.40
     Сак
    0.40
     XE
    0.38
     сър
    0.38
    பிலோ
    0.37
    Wish
    0.36
    GROUND
    0.36
     कपड़े
    0.36
     Xing
    0.36
     SpaceX
    0.36
    POSITIVE LOGITS
    পন্ন
    0.41
     tsd
    0.38
     Constructs
    0.37
    徎
    0.37
     assign
    0.36
     पूर्
    0.36
     Portraits
    0.36
     poset
    0.36
     tabla
    0.35
    ènes
    0.35
    Activations Density 0.000%

    No Known Activations