© 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
    2. Gemma-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 51975
    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_55_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
    ('(
    0.43
     though
    0.37
    though
    0.36
    however
    0.36
    ','.
    0.35
    ('').
    0.35
    ('-
    0.34
    influenced
    0.33
    veloped
    0.33
    arkan
    0.32
    POSITIVE LOGITS
    ,/
    0.72
     /
    0.66
    ;/
    0.55
     /\
    0.54
     Of
    0.50
     $/
    0.50
    /
    0.49
     And
    0.48
    -/
    0.47
    :/
    0.46
    Activations Density 0.018%

    No Known Activations