© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 64973
    Prev
    Next
    INDEX
    Explanations

    fi

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     ನಡೆ
    0.45
    คู่
    0.39
    렀
    0.39
     التس
    0.38
    utes
    0.38
    uiden
    0.38
    ))=\
    0.36
    뉴스
    0.36
    ushes
    0.36
    関西
    0.36
    POSITIVE LOGITS
    ENIX
    0.48
    Bridge
    0.42
    psilon
    0.40
     Kak
    0.39
    ño
    0.39
     Phoenix
    0.38
    Acet
    0.38
     Quint
    0.38
    Ris
    0.38
    த்தன
    0.38
    Activations Density 0.000%

    No Known Activations