© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35125
    Prev
    Next
    INDEX
    Explanations

    Elimination Round

    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
    Negative Logits
    Les
    0.63
    Quality
    0.61
    Luxury
    0.60
    Tiempo
    0.57
    Things
    0.56
    𝑭
    0.56
    Czas
    0.55
    Forgot
    0.55
    Consult
    0.55
    Theatre
    0.54
    POSITIVE LOGITS
    en
    0.76
    r
    0.74
    '
    0.74
    n
    0.72
    ov
    0.71
     as
    0.70
    ar
    0.70
    as
    0.67
    es
    0.66
    ni
    0.64
    Activations Density 0.001%

    No Known Activations