© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39856
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    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_57_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
    менты
    0.37
    tire
    0.36
     ಮೂಲ
    0.36
    मनी
    0.35
    最大の
    0.35
    Ꮽ
    0.35
    mentioned
    0.34
     أهم
    0.34
     பிரமி
    0.34
    部門
    0.34
    POSITIVE LOGITS
    mnopqr
    0.44
    淒
    0.42
     Ln
    0.41
     Pi
    0.41
     smarter
    0.41
    Elems
    0.40
     U
    0.40
     u
    0.40
     सैयद
    0.39
     i
    0.38
    Activations Density 0.014%

    No Known Activations