© 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. 21276
    Prev
    Next
    INDEX
    Explanations

    say ">"

    np_max-act-logits · gemini-2.5-flash-lite
    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
     $\
    0.59
     more
    0.54
    $\
    0.51
     أكثر
    0.49
     اكثر
    0.49
    more
    0.49
     अधिक
    0.48
     =&
    0.48
     MORE
    0.46
    }&\
    0.46
    POSITIVE LOGITS
     >
    0.45
    greater
    0.42
     grada
    0.42
     *
    0.39
     Clubhouse
    0.38
     //
    0.37
    শাল
    0.37
     Compression
    0.37
     Condensed
    0.37
    Decrement
    0.37
    Activations Density 0.012%

    No Known Activations