© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138430
    Prev
    Next
    INDEX
    Explanations

    Ros

    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_46_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
     দেবযানী
    0.43
    iele
    0.43
     Gillian
    0.40
    "]="
    0.37
    maked
    0.37
     Pack
    0.36
    ीड
    0.36
     Dokl
    0.36
    "];
    0.36
     നേ
    0.36
    POSITIVE LOGITS
    ազ
    0.38
     emociones
    0.37
     lighthouse
    0.36
     authorship
    0.36
     табы
    0.36
     Lighthouse
    0.35
    字典
    0.34
    赤
    0.34
    而去
    0.34
    হাম্ম
    0.34
    Activations Density 0.000%

    No Known Activations