© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205476
    Prev
    Next
    INDEX
    Explanations

    Baghdad

    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_6_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
    bins
    0.93
     ਕ
    0.91
    হরণ
    0.91
     بہت
    0.89
     ҳам
    0.89
     ရှိ
    0.88
     یا
    0.88
    hika
    0.88
     בה
    0.87
     ゆ
    0.86
    POSITIVE LOGITS
    s
    1.58
    س
    1.18
    -
    1.13
    يس
    1.07
    ס
    1.04
    m
    1.03
    <0x0D>
    0.95
    ви
    0.94
    </sup>
    0.92
    య
    0.89
    Activations Density 0.000%

    No Known Activations