© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105164
    Prev
    Next
    INDEX
    Explanations

    create jobs and opportunities

    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_1_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
    の
    1.23
    не
    1.17
    의
    1.13
    장
    1.13
    <0x0D>
    1.10
    s
    1.10
    ان
    1.08
    사
    1.08
     is
    1.07
    ат
    1.07
    POSITIVE LOGITS
    ek
    0.94
    д
    0.94
    oot
    0.92
    ۰
    0.86
    iro
    0.81
    ő
    0.79
     If
    0.79
    dehyde
    0.78
    oom
    0.77
    ource
    0.77
    Activations Density 0.001%

    No Known Activations