© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35476
    Prev
    Next
    INDEX
    Explanations

    condensation forming or dripping

    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_11_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
    </strong>
    0.74
     not
    0.70
    </h2>
    0.66
    </b>
    0.64
     Chapter
    0.62
     отрима
    0.61
     impug
    0.59
    !
    0.59
    amo
    0.58
     notices
    0.57
    POSITIVE LOGITS
     destacó
    0.59
    т
    0.58
    त
    0.58
    л
    0.58
     kereszt
    0.56
    స్‌
    0.55
     చేసి
    0.55
    MovieList
    0.55
    ки
    0.54
    SpecID
    0.54
    Activations Density 0.003%

    No Known Activations