© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53222
    Prev
    Next
    INDEX
    Explanations

    smaller or less

    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
     aument
    0.76
     increases
    0.76
     aumenta
    0.75
     zwięks
    0.73
     increased
    0.71
    が増
    0.71
     zvyš
    0.71
    増
    0.70
     higher
    0.69
     повышен
    0.69
    POSITIVE LOGITS
    Smaller
    0.59
     shortening
    0.58
     Smaller
    0.58
     shorter
    0.53
     shortened
    0.53
     shorten
    0.53
    Low
    0.52
    smaller
    0.52
    LOW
    0.52
     slimmer
    0.52
    Activations Density 0.003%

    No Known Activations