© 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. 39090
    Prev
    Next
    INDEX
    Explanations

    seaports, seafaring, airplane

    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
    in
    1.04
    v
    0.88
    z
    0.83
    ete
    0.76
    im
    0.75
    هم
    0.74
    ні
    0.73
    sp
    0.72
    hel
    0.70
    for
    0.69
    POSITIVE LOGITS
    고
    0.84
    اريخ
    0.76
     шесть
    0.74
     بسي
    0.73
    За
    0.70
     نہيں
    0.66
     مدير
    0.66
    ت
    0.66
     drie
    0.65
     subsid
    0.64
    Activations Density 0.000%

    No Known Activations