© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144540
    Prev
    Next
    INDEX
    Explanations

    declensions or declavings

    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_0_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
    ו
    2.17
    l
    1.92
    i
    1.79
    -
    1.72
    at
    1.52
    an
    1.39
    י
    1.38
    r
    1.37
    n
    1.34
    ul
    1.32
    POSITIVE LOGITS
     for
    1.54
     which
    1.50
    ک
    1.45
     or
    1.39
     automate
    1.35
    ड
    1.34
     if
    1.32
    ார்
    1.31
     }
    1.25
     gioco
    1.24
    Activations Density 0.001%

    No Known Activations