© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210390
    Prev
    Next
    INDEX
    Explanations

    with a, to see, to ensure

    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_10_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
     अवसरों
    0.72
    బ్యా
    0.71
     cerrada
    0.68
     williams
    0.68
    MANAG
    0.66
     खाता
    0.66
     WILLIAMS
    0.65
    袭
    0.65
     اندراج
    0.64
     వ్యవస్థ
    0.64
    POSITIVE LOGITS
    ↵
    0.94
     był
    0.63
    </h1>
    0.63
    jší
    0.61
    al
    0.59
    </
    0.58
    },
    0.57
     di
    0.57
     for
    0.56
     but
    0.56
    Activations Density 0.015%

    No Known Activations