© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112811
    Prev
    Next
    INDEX
    Explanations

    infrastructure

    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_2_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
    ill
    0.93
    𝐌
    0.93
    rives
    0.89
     Nähe
    0.88
    ﻟ
    0.88
    称号
    0.87
    ru
    0.87
    ر
    0.86
    什
    0.86
    the
    0.85
    POSITIVE LOGITS
     as
    1.99
     are
    1.54
     at
    1.43
    is
    1.37
     about
    1.34
    ية
    1.32
     on
    1.30
     that
    1.22
     by
    1.22
    것
    1.21
    Activations Density 0.006%

    No Known Activations