© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50054
    Prev
    Next
    INDEX
    Explanations

    independently drive projects

    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_30_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
     décadas
    0.41
     diversification
    0.41
    ഹം
    0.40
     ৬৬
    0.40
    욘
    0.38
    क्ष्य
    0.38
     പരിച
    0.38
    펨
    0.37
    我已经
    0.37
     diversifying
    0.37
    POSITIVE LOGITS
    {//
    0.42
    ﻐ
    0.38
    wau
    0.37
     contribution
    0.35
    yti
    0.35
    agd
    0.35
    monary
    0.34
    epine
    0.34
     laminated
    0.34
    furter
    0.34
    Activations Density 0.006%

    No Known Activations