© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156530
    Prev
    Next
    INDEX
    Explanations

    inhaling

    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
    na
    1.09
    는
    1.04
    es
    0.93
    6
    0.93
    this
    0.93
     النظر
    0.89
    in
    0.89
    ia
    0.88
    that
    0.88
    กัน
    0.88
    POSITIVE LOGITS
     underestimates
    1.19
    ص
    1.18
    ἲ
    1.13
     for
    1.11
    ر
    1.10
    𝐜
    1.09
    ೀಯ
    1.05
    ೆ
    1.05
    ﺀ
    1.01
     be
    1.00
    Activations Density 0.000%

    No Known Activations