© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197213
    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_26_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
     huis
    0.53
    _
    0.52
     recollections
    0.48
     impediments
    0.47
     Герма
    0.46
     simp
    0.46
     Rumah
    0.45
     arrhythmias
    0.45
    Hist
    0.44
     cancellations
    0.44
    POSITIVE LOGITS
    с
    0.55
    e
    0.55
    ți
    0.47
    𝒆
    0.47
     사용자
    0.47
     دارای
    0.46
    י
    0.45
    𝚎
    0.45
    leq
    0.44
    process
    0.44
    Activations Density 0.000%

    No Known Activations