© 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. 37886
    Prev
    Next
    INDEX
    Explanations

    erosion

    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
    9
    0.64
     bleach
    0.62
    était
    0.55
    NING
    0.55
    8
    0.54
     was
    0.54
     całkow
    0.52
    UTTON
    0.51
    AK
    0.50
     ৭৭
    0.50
    POSITIVE LOGITS
    ل
    0.59
    glomer
    0.55
    فضل
    0.54
    ियर
    0.53
    รัฐ
    0.52
    cionario
    0.52
     heres
    0.52
    事情
    0.51
    comput
    0.51
    gitignore
    0.51
    Activations Density 0.003%

    No Known Activations