© 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. 61659
    Prev
    Next
    INDEX
    Explanations

    past tense auxiliary verb

    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
    מ
    1.50
     is
    1.46
     that
    1.36
    ק
    1.30
    ה
    1.27
    ’
    1.18
    :
    1.12
    ق
    1.11
    א
    1.11
    RA
    1.10
    POSITIVE LOGITS
    op
    1.32
    ről
    1.25
    ow
    1.15
    are
    1.13
    ip
    1.09
    ut
    1.07
    ición
    1.00
    il
    1.00
    hung
    0.98
    rue
    0.95
    Activations Density 0.001%

    No Known Activations