© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92159
    Prev
    Next
    INDEX
    Explanations

    hanging in the balance

    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_11_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
     flashed
    0.64
     French
    0.57
     Entfer
    0.56
    ois
    0.55
     เหน
    0.55
     বাহ
    0.55
    ۍ
    0.55
    জার
    0.54
     trac
    0.54
     Frankreich
    0.54
    POSITIVE LOGITS
     samh
    0.51
    コロ
    0.49
     colony
    0.48
     вода
    0.47
     lockdowns
    0.46
    Maze
    0.46
     sirven
    0.46
    interactions
    0.45
    }
    0.44
    rake
    0.44
    Activations Density 0.002%

    No Known Activations