© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14245
    Prev
    Next
    INDEX
    Explanations

    multiple elements or items

    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
    ⌋
    0.47
    aminar
    0.39
    段
    0.38
    βά
    0.38
    洴
    0.38
    ût
    0.37
     घोष
    0.37
     суу
    0.37
     ডলার
    0.37
    屶
    0.37
    POSITIVE LOGITS
     elements
    0.85
     observations
    0.82
    observations
    0.81
     items
    0.80
     Elements
    0.78
     Items
    0.77
     values
    0.76
     Observations
    0.74
     elementos
    0.73
    items
    0.72
    Activations Density 0.241%

    No Known Activations