© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    at least

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    是
    0.49
    ဖြေ
    0.46
    کا
    0.45
    는
    0.44
    ),
    0.44
    レンダー
    0.44
    नेशनल
    0.43
    ᒻ
    0.43
    )。
    0.42
    ก็
    0.42
    POSITIVE LOGITS
     හැ
    0.46
     playfully
    0.45
     φ
    0.41
    albeit
    0.41
     Municip
    0.39
     Δια
    0.39
    </strong>
    0.39
     тря
    0.39
     ፍ
    0.38
     \
    0.38
    Activations Density 0.025%

    No Known Activations