© 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. 40854
    Prev
    Next
    INDEX
    Explanations

    African country?

    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
    '
    1.19
    ৫
    0.77
    -
    0.76
    দের
    0.74
    の
    0.73
    >
    0.72
    𐰚
    0.72
    ные
    0.71
    вающей
    0.71
    \,\
    0.68
    POSITIVE LOGITS
    n
    0.72
    rt
    0.71
    its
    0.68
    nine
    0.68
    all
    0.67
    lt
    0.67
    ier
    0.66
     insurgency
    0.66
     इच्छुक
    0.64
    tt
    0.64
    Activations Density 0.003%

    No Known Activations