© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11235
    Prev
    Next
    INDEX
    Explanations

    glass

    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
    Outcome
    0.39
     सुधा
    0.38
     musique
    0.37
     vig
    0.37
    GOLD
    0.37
     ውጤ
    0.36
    빔
    0.36
     ذه
    0.36
     Projection
    0.36
    uthi
    0.36
    POSITIVE LOGITS
     glass
    2.09
     Glass
    1.89
    Glass
    1.86
    玻璃
    1.78
    glass
    1.77
     GLASS
    1.62
    ガラス
    1.60
    GLASS
    1.51
     ग्लास
    1.42
     ガラス
    1.39
    Activations Density 0.027%

    No Known Activations