© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90282
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations ending in 'cs' or 'cm'

    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
    颦
    0.66
    ,:)
    0.63
    ک
    0.63
    icast
    0.62
     ظِلِّ
    0.62
    testen
    0.59
     целях
    0.57
     издания
    0.57
    纍
    0.57
    )’
    0.57
    POSITIVE LOGITS
    at
    0.86
    '
    0.85
    t
    0.80
    of
    0.79
    y
    0.75
    ve
    0.75
    d
    0.73
    al
    0.73
    >
    0.72
    x
    0.69
    Activations Density 0.010%

    No Known Activations