© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 212946
    Prev
    Next
    INDEX
    Explanations

    recall, identify, explain

    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_16_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
     PROBLE
    0.44
     punkt
    0.42
     Proble
    0.42
    ang
    0.39
     Yuan
    0.39
     photospheric
    0.39
     Punkt
    0.38
    𝙃
    0.38
     Eropa
    0.38
     Еўро
    0.37
    POSITIVE LOGITS
    方法的
    0.48
    函数的
    0.42
    ёнок
    0.40
     ricordo
    0.37
    ()),
    0.36
     ד
    0.36
     remembers
    0.34
    ARTI
    0.34
    数的
    0.34
     sẻ
    0.33
    Activations Density 0.043%

    No Known Activations