© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43566
    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_13_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
     maroon
    0.54
    f
    0.48
    itone
    0.47
     cheek
    0.46
     breast
    0.45
     illnesses
    0.45
    ed
    0.45
     doubling
    0.45
    forcements
    0.45
     erecting
    0.45
    POSITIVE LOGITS
    B
    0.57
    گاہ
    0.53
    جنة
    0.51
    L
    0.50
    ب
    0.49
    َع
    0.48
    бі
    0.48
    )));
    0.47
    Don
    0.46
    setDate
    0.46
    Activations Density 0.000%

    No Known Activations