© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251123
    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_56_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
     naszym
    0.39
    ellem
    0.37
    jskim
    0.37
     Cram
    0.35
    )}$
    0.35
    当量
    0.34
    elem
    0.33
     Wyman
    0.33
     нашим
    0.33
    param
    0.32
    POSITIVE LOGITS
    ukka
    0.34
     origina
    0.34
    vues
    0.34
    怆
    0.34
     sete
    0.33
    ูด
    0.32
    uced
    0.31
    🆚
    0.31
    íns
    0.31
    ಷ್
    0.31
    Activations Density 0.000%

    No Known Activations