© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10314
    Prev
    Next
    INDEX
    Explanations

    porous materialstats

    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_13_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
    skar
    0.55
     Übersicht
    0.53
    Widget
    0.52
     '
    0.51
     widget
    0.48
    garh
    0.48
    swürdig
    0.47
    modation
    0.47
    সাধ
    0.46
    ד
    0.46
    POSITIVE LOGITS
     hơn
    0.59
     aphids
    0.57
    ઓ
    0.57
     estrogens
    0.56
    ﭑ
    0.55
     Ирина
    0.54
     Emperor
    0.52
     partita
    0.49
     спе
    0.48
     spices
    0.48
    Activations Density 0.014%

    No Known Activations