© 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. 85923
    Prev
    Next
    INDEX
    Explanations

    wavelengths and wheelbase

    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
    </h3>
    1.06
    </h5>
    0.81
    </th>
    0.75
    </h6>
    0.74
    <0x0D>
    0.68
    </h1>
    0.67
    pm
    0.65
    pping
    0.65
    </h4>
    0.64
    ta
    0.64
    POSITIVE LOGITS
    не
    0.87
    t
    0.85
     for
    0.82
    ار
    0.82
    র
    0.75
    ન
    0.75
    е
    0.72
     exécut
    0.70
    ни
    0.68
     complicaciones
    0.68
    Activations Density 0.001%

    No Known Activations