© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90624
    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_60_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
    bordered
    0.39
    5
    0.38
    creation
    0.38
     already
    0.38
     différent
    0.38
     arbej
    0.37
    completely
    0.37
     WORKING
    0.37
    favorite
    0.37
    ᱕
    0.37
    POSITIVE LOGITS
    사와
    0.39
    Mà
    0.39
     Crowley
    0.38
    ropath
    0.36
    հ
    0.36
    *",
    0.35
    ECE
    0.35
    Џ
    0.35
    ალ
    0.35
     Eck
    0.35
    Activations Density 0.000%

    No Known Activations