© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82329
    Prev
    Next
    INDEX
    Explanations

    molecules

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     Night
    0.37
     manifolds
    0.37
    ەل
    0.36
     Nights
    0.35
     Horne
    0.35
    refs
    0.34
    ение
    0.34
    涜
    0.34
     Ceremony
    0.34
     ومل
    0.34
    POSITIVE LOGITS
    分子
    0.92
     molecules
    0.69
     Molecules
    0.69
     molecular
    0.67
    Molecular
    0.67
     molecule
    0.66
     Molecular
    0.64
     молеку
    0.64
    molecular
    0.63
     moléculas
    0.60
    Activations Density 0.000%

    No Known Activations