© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40685
    Prev
    Next
    INDEX
    Explanations

    absolute beginner

    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_3_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
    ፩
    0.62
     Pemerintah
    0.58
     Meskipun
    0.57
    一張
    0.57
    awan
    0.56
    是一個
    0.54
     Eugène
    0.54
     NavBar
    0.53
    ?
    0.53
     antiguo
    0.51
    POSITIVE LOGITS
     in
    0.90
    在
    0.73
    ໃນ
    0.71
    in
    0.69
     في
    0.67
    𝕝
    0.64
    ુ
    0.63
    𝕤
    0.63
    )、
    0.60
    ión
    0.58
    Activations Density 0.006%

    No Known Activations