© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47195
    Prev
    Next
    INDEX
    Explanations

    newborn

    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
    Negative Logits
    ل
    0.92
    st
    0.91
    la
    0.79
    tte
    0.79
    lr
    0.74
    nis
    0.73
    t
    0.72
    mk
    0.71
    source
    0.70
    lt
    0.69
    POSITIVE LOGITS
    će
    0.70
     svojoj
    0.68
    a
    0.68
    iré
    0.67
    }=\
    0.66
    та
    0.66
    يد
    0.66
    AN
    0.65
    is
    0.65
    EN
    0.65
    Activations Density 0.001%

    No Known Activations