© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 251786
    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
     եւ
    0.41
    ‥
    0.39
    ,…
    0.38
    等は
    0.38
    repl
    0.38
    /~
    0.38
    utilise
    0.37
    𝑅
    0.37
     இருக்கு
    0.36
     şi
    0.36
    POSITIVE LOGITS
     altos
    0.37
    ాన్ని
    0.37
     H
    0.36
     TypeToken
    0.36
    ానికి
    0.35
     Seahawks
    0.33
     Process
    0.33
     junior
    0.33
    轸
    0.33
     कथित
    0.32
    Activations Density 0.000%

    No Known Activations