© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3676
    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
    统
    0.39
     enquête
    0.39
     uniformed
    0.38
    ుల
    0.37
    자를
    0.37
    langle
    0.36
     掛
    0.35
    仹
    0.35
     "\""
    0.34
    を守
    0.34
    POSITIVE LOGITS
     constitut
    0.42
    ঔ
    0.41
     ná
    0.38
    Constit
    0.37
     cursorPos
    0.37
    ιδ
    0.36
    တင်
    0.36
     संविधान
    0.36
     Ahmet
    0.35
     Constitu
    0.35
    Activations Density 0.000%

    No Known Activations