© 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. 232442
    Prev
    Next
    INDEX
    Explanations

    compiling or competing

    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
    ني
    0.90
    </b>
    0.89
    ના
    0.88
    ين
    0.84
    </h3>
    0.83
    <0x0D>
    0.82
    نا
    0.79
    <0x8A>
    0.79
    <0x85>
    0.78
     mají
    0.77
    POSITIVE LOGITS
    is
    1.25
    1
    1.19
    as
    1.00
    وم
    0.96
     to
    0.90
    at
    0.90
    ات
    0.83
    0
    0.82
    3
    0.79
    m
    0.78
    Activations Density 0.003%

    No Known Activations