© 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. 161389
    Prev
    Next
    INDEX
    Explanations

    Chinese Pinyin syllables

    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
     are
    1.50
     can
    1.22
    ];
    1.22
     sabot
    1.16
     as
    1.13
    ুল
    1.10
     jeopard
    1.09
     dyed
    1.07
     but
    1.06
     don
    1.06
    POSITIVE LOGITS
    of
    1.93
    in
    1.38
    g
    1.35
    gruppe
    1.28
    i
    1.28
    -
    1.28
    p
    1.27
    al
    1.24
    giveness
    1.23
    ات
    1.18
    Activations Density 0.000%

    No Known Activations