© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76753
    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_31_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
     PMID
    0.43
    chließlich
    0.40
     მთავ
    0.40
    𝔞
    0.40
     মেশ
    0.39
    下來
    0.39
     SPT
    0.39
     धर्मा
    0.39
     JOptionPane
    0.39
     വർഷ
    0.39
    POSITIVE LOGITS
     intercepts
    0.37
     Jewish
    0.37
    尊
    0.37
    Jewish
    0.36
    island
    0.35
     کره
    0.34
    PE
    0.33
    broad
    0.33
    questions
    0.33
    Broad
    0.33
    Activations Density 0.000%

    No Known Activations