© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13804
    Prev
    Next
    INDEX
    Explanations

    superlatives and extremes

    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_40_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
    ClrType
    0.36
    েন্স
    0.34
    ORMAL
    0.34
    院
    0.34
     ازاي
    0.33
     yard
    0.33
    enity
    0.33
    dding
    0.33
    .".
    0.33
    {:
    0.33
    POSITIVE LOGITS
     strongest
    0.95
     nhất
    0.85
     가장
    0.84
     सबसे
    0.83
     easiest
    0.82
     সবচেয়ে
    0.82
     najbardziej
    0.82
     brightest
    0.81
     weakest
    0.80
     সবচেয়ে
    0.79
    Activations Density 0.071%

    No Known Activations