© 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. 250967
    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
     way
    0.49
     paper
    0.37
    way
    0.37
     вет
    0.35
     Jay
    0.34
     façon
    0.34
    </u>
    0.33
    해서
    0.33
     մե
    0.33
     Happ
    0.32
    POSITIVE LOGITS
     Directed
    0.43
    Designed
    0.42
     রচিত
    0.42
    Trace
    0.41
    Long
    0.41
    Str
    0.40
     Designed
    0.40
     grand
    0.40
    BOR
    0.39
    Built
    0.39
    Activations Density 0.000%

    No Known Activations