© 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. 157874
    Prev
    Next
    INDEX
    Explanations

    verbs describing actions or events

    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
    א
    1.15
    ן
    1.02
    י
    1.00
    ש
    0.95
    ни
    0.92
    dır
    0.92
    ח
    0.92
    ك
    0.91
    ד
    0.91
    다
    0.88
    POSITIVE LOGITS
     and
    0.98
    ként
    0.97
    我们
    0.96
    美国
    0.93
    的
    0.92
    CGPoint
    0.91
    你
    0.89
     Հ
    0.89
    新
    0.89
     fakta
    0.88
    Activations Density 0.003%

    No Known Activations