© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148669
    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_59_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
     be
    0.46
     also
    0.46
     Be
    0.46
     Kan
    0.44
     Holland
    0.42
     A
    0.42
     MDR
    0.41
     වර්ග
    0.38
    μένα
    0.38
     #{
    0.37
    POSITIVE LOGITS
    Harrison
    0.39
    aný
    0.38
    elecimento
    0.38
    ляю
    0.37
     Ust
    0.36
    Deve
    0.36
    奂
    0.36
    lada
    0.36
    Developing
    0.35
    lação
    0.35
    Activations Density 0.000%

    No Known Activations