© 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. 162445
    Prev
    Next
    INDEX
    Explanations

    needed to be

    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
    u
    2.13
    _
    1.66
    ת
    1.51
    0
    1.35
    o
    1.34
    ing
    1.33
    e
    1.33
     on
    1.32
    ات
    1.32
    3
    1.28
    POSITIVE LOGITS
    ας
    1.38
    ાર
    1.23
    п
    1.13
    اک
    1.10
    стью
    1.08
    рав
    1.07
    ви
    1.03
    ра
    1.01
    բ
    1.01
     \
    1.00
    Activations Density 0.002%

    No Known Activations