© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201583
    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_12_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
    p
    0.66
    .)
    0.59
     terrib
    0.58
    ol
    0.57
    t
    0.57
    album
    0.55
    ).[
    0.54
    .[
    0.54
     viernes
    0.52
     Assass
    0.52
    POSITIVE LOGITS
    하지
    0.52
    사회
    0.51
    OLS
    0.49
    yaan
    0.49
    েন্টস
    0.49
    нк
    0.49
    бия
    0.49
    yati
    0.48
     sparring
    0.48
    ディース
    0.48
    Activations Density 0.000%

    No Known Activations