© 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. 126196
    Prev
    Next
    INDEX
    Explanations

    isoprenaline, isoflavor

    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
    ن
    0.92
    an
    0.85
    with
    0.85
    не
    0.82
    И
    0.82
    О
    0.80
    ೋಜನ
    0.80
    푞
    0.80
    Ми
    0.79
    ið
    0.79
    POSITIVE LOGITS
     as
    0.82
     on
    0.70
     o
    0.70
     are
    0.68
    ัก
    0.68
     The
    0.64
    "
    0.64
     $
    0.63
     augmenting
    0.60
    </h3>
    0.59
    Activations Density 0.000%

    No Known Activations