© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61064
    Prev
    Next
    INDEX
    Explanations

    Evelyn

    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
    ى
    1.46
    د
    1.23
    ст
    1.18
    но
    1.15
    <0x80>
    1.10
    dbjc
    1.06
    த்தில்
    1.05
    рила
    1.05
    <0x93>
    1.04
    ずっと
    1.04
    POSITIVE LOGITS
    ן
    1.35
     for
    1.20
    ation
    1.15
    ת
    1.11
    ă
    1.05
     that
    1.02
    ového
    0.95
    </h3>
    0.94
    oses
    0.91
    ING
    0.90
    Activations Density 0.000%

    No Known Activations