© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103930
    Prev
    Next
    INDEX
    Explanations

    Eggs as a protein source

    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_1_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
    \
    1.16
    _
    1.07
     in
    1.01
     of
    0.96
    8
    0.94
     as
    0.88
     semifinals
    0.84
     ότι
    0.82
    6
    0.81
    </td>
    0.79
    POSITIVE LOGITS
    n
    0.92
    typen
    0.91
    د
    0.88
    ל
    0.83
    ன்
    0.82
    درا
    0.82
     compteur
    0.77
    ک
    0.77
    го
    0.76
    that
    0.75
    Activations Density 0.004%

    No Known Activations