© 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. 61416
    Prev
    Next
    INDEX
    Explanations

    words ending in ing

    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
    ا
    1.65
    at
    1.54
    가
    1.41
     that
    1.38
    ла
    1.37
    ي
    1.37
    ра
    1.29
    ба
    1.27
    م
    1.25
    ور
    1.23
    POSITIVE LOGITS
    t
    1.69
    r
    1.24
    ない
    1.09
     Mục
    1.06
    टेट
    1.02
    x
    1.00
     remov
    0.99
     announc
    0.99
    p
    0.98
    rda
    0.98
    Activations Density 0.000%

    No Known Activations