© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162441
    Prev
    Next
    INDEX
    Explanations

    binary search mid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     Analysis
    0.44
    姿
    0.40
     watching
    0.38
     analyzing
    0.38
     analysis
    0.37
     ANALYSIS
    0.37
     Measure
    0.37
     ทด
    0.37
     Arct
    0.37
     trasporto
    0.37
    POSITIVE LOGITS
    顺
    0.40
     adjacent
    0.38
     unavailability
    0.38
     dangerously
    0.37
     consecutively
    0.37
    ި
    0.36
    觊
    0.36
    盗
    0.35
    ís
    0.35
     contiguous
    0.35
    Activations Density 0.001%

    No Known Activations