© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132673
    Prev
    Next
    INDEX
    Explanations

    cover letter phrases

    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_50_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
    取り組み
    0.38
     Seah
    0.38
    dX
    0.38
    Pokémon
    0.37
    较
    0.37
    较高的
    0.37
     gobl
    0.37
    ~~~~~~~~~~~~~~~~
    0.37
    ക്കാല
    0.37
     মহার
    0.36
    POSITIVE LOGITS
     bi
    0.45
     kerosene
    0.44
     biometric
    0.43
    bi
    0.43
     Tus
    0.40
     Kru
    0.40
     Vos
    0.40
     моей
    0.39
     Lamp
    0.39
     عندي
    0.38
    Activations Density 0.001%

    No Known Activations