© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6232
    Prev
    Next
    INDEX
    Explanations

    building and defining concepts

    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
    understood
    0.25
     currentChar
    0.24
     understood
    0.24
    ルトラ
    0.23
    鐺
    0.23
    知識
    0.23
     čern
    0.23
    orith
    0.23
    istory
    0.22
    嬪
    0.22
    POSITIVE LOGITS
     representation
    0.37
     representations
    0.37
     Representations
    0.31
     Representation
    0.31
    Representation
    0.28
     représentation
    0.28
     Illustrations
    0.27
     przedstaw
    0.27
     illustrated
    0.26
    representations
    0.25
    Activations Density 0.034%

    No Known Activations