© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142384
    Prev
    Next
    INDEX
    Explanations

    NSA

    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_12_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
    нде
    0.16
     nared
    0.16
    werten
    0.16
    ’
    0.16
    toMatch
    0.15
    حية
    0.15
    equivalent
    0.14
     inteligencia
    0.14
     survey
    0.14
    )
    0.14
    POSITIVE LOGITS
    ✿
    0.18
     वापस
    0.16
    ロット
    0.16
     săptăm
    0.16
     सप्ताह
    0.16
     professionnelle
    0.16
     thorns
    0.16
     সেখানে
    0.15
     ความ
    0.15
     ショルダーバッグ
    0.15
    Activations Density 0.001%

    No Known Activations