© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34648
    Prev
    Next
    INDEX
    Explanations

    Adam and Eve

    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
    Not in Any Lists

    No Comments

    Negative Logits
    u
    0.74
    ل
    0.71
    <0x0D>
    0.65
    mse
    0.65
    </h2>
    0.63
    ب
    0.63
    st
    0.63
    c
    0.62
    </h3>
    0.61
    د
    0.60
    POSITIVE LOGITS
     buildFor
    0.71
     gosto
    0.65
     râ
    0.59
    AR
    0.58
    AN
    0.58
     tá
    0.57
     thrive
    0.57
     końca
    0.57
     فِي
    0.57
     conducir
    0.57
    Activations Density 0.008%

    No Known Activations