© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36583
    Prev
    Next
    INDEX
    Explanations

    Sally-Anne test

    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_3_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
    shifts
    0.70
    )
    0.67
    tow
    0.66
    slice
    0.65
    kills
    0.63
    end
    0.62
    ).
    0.62
    toMap
    0.62
    tile
    0.61
    toe
    0.61
    POSITIVE LOGITS
    an
    0.82
    ва
    0.72
    l
    0.71
    к
    0.71
     is
    0.69
     erroneously
    0.68
    н
    0.68
    j
    0.67
     pretensions
    0.66
     on
    0.65
    Activations Density 0.002%

    No Known Activations