© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1890
    Prev
    Next
    INDEX
    Explanations

    pull

    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_40_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
     compressed
    0.41
     압
    0.40
     compressibility
    0.40
    晎
    0.40
     пресс
    0.39
     الموج
    0.39
     compresses
    0.38
     вер
    0.37
    μών
    0.37
    Shortcut
    0.37
    POSITIVE LOGITS
     pull
    2.27
     pulling
    2.20
     Pull
    2.19
     pulls
    2.14
    pull
    2.13
    Pull
    2.11
     pulled
    2.03
    拉
    1.66
     pux
    1.55
     tug
    1.52
    Activations Density 0.108%

    No Known Activations