© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193219
    Prev
    Next
    INDEX
    Explanations

    mmh / mph sounds

    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_4_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
    ला
    1.20
    ای
    1.15
    ח
    1.09
    ק
    1.01
    ই
    0.94
    エ
    0.91
    UT
    0.90
     کھیلیں
    0.89
    구
    0.89
    টি
    0.88
    POSITIVE LOGITS
    m
    0.85
    。
    0.82
     ت
    0.82
     م
    0.77
     أد
    0.75
    ‬
    0.75
    </h3>
    0.75
    )。
    0.75
    '
    0.74
     في
    0.73
    Activations Density 0.001%

    No Known Activations