© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131008
    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_25_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
    قلال
    0.44
    定
    0.42
    ያንዳ
    0.41
     spectator
    0.40
    ದಲು
    0.37
     ၂
    0.37
    દ
    0.36
     strutt
    0.36
    Accepted
    0.36
    琬
    0.36
    POSITIVE LOGITS
     como
    0.43
     aberrations
    0.41
    как
    0.40
    robots
    0.39
     redundant
    0.39
     haar
    0.38
    \})
    0.38
     robots
    0.38
    NR
    0.37
    como
    0.37
    Activations Density 0.000%

    No Known Activations