© 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. 166642
    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
     !\
    0.44
     !!!!!
    0.44
     !",
    0.43
     !!!!
    0.42
     Properly
    0.39
     Typically
    0.39
    𝒐
    0.38
     Proper
    0.38
     !!,
    0.37
     !!!
    0.36
    POSITIVE LOGITS
     wee
    0.66
     flat
    0.61
    Flat
    0.59
     Flat
    0.59
    flat
    0.55
     फ्लैट
    0.51
    平
    0.49
     flats
    0.47
     FLAT
    0.47
     Wee
    0.46
    Activations Density 0.000%

    No Known Activations