© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159743
    Prev
    Next
    INDEX
    Explanations

    `chkdsk` command and Russian place names

    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_2_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
    та
    2.06
    м
    1.59
    ق
    1.55
    ع
    1.52
    م
    1.37
    ك
    1.31
    ו
    1.31
    ம்
    1.30
    ת
    1.30
    да
    1.27
    POSITIVE LOGITS
    o
    1.37
    the
    1.18
    .
    1.16
    e
    1.09
    i
    1.07
    a
    1.05
    ed
    0.91
    r
    0.91
    an
    0.90
     digital
    0.89
    Activations Density 0.001%

    No Known Activations