© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75782
    Prev
    Next
    INDEX
    Explanations

    past tense verbs that interact

    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_31_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
    лье
    0.34
     Lek
    0.33
    cate
    0.32
    kungan
    0.32
     spatial
    0.32
    升级
    0.31
    ᱗
    0.31
     rose
    0.31
    错了
    0.31
    unciation
    0.31
    POSITIVE LOGITS
     ಅನುಪಾತ
    0.36
     defies
    0.33
     Bourg
    0.31
     trifft
    0.30
    圧力
    0.30
     hubs
    0.30
    awiają
    0.29
    Src
    0.29
    Demand
    0.29
    υ
    0.29
    Activations Density 0.000%

    No Known Activations