© 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. 128019
    Prev
    Next
    INDEX
    Explanations

    Project Phoenix

    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
    ين
    0.76
    ों
    0.70
    ת
    0.68
    দের
    0.66
    ים
    0.66
    та
    0.64
    ே
    0.64
    ের
    0.64
    тран
    0.59
    ျ
    0.59
    POSITIVE LOGITS
     at
    0.59
    RE
    0.58
     vagina
    0.57
     губерна
    0.56
    )²
    0.55
    ")
    0.54
     headroom
    0.49
    ア
    0.49
     tän
    0.49
    場合に
    0.49
    Activations Density 0.002%

    No Known Activations