© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243188
    Prev
    Next
    INDEX
    Explanations

    requires_grad=True gradients

    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
    ધાન
    0.39
    ིན་
    0.38
     디
    0.38
    RESH
    0.38
     Kline
    0.37
     пово
    0.37
     поверну
    0.37
     hans
    0.35
    的手
    0.35
    Mild
    0.35
    POSITIVE LOGITS
    遵
    0.41
    ֒
    0.40
     manzanas
    0.40
     olímp
    0.38
    臬
    0.38
     kon
    0.37
    <0x0F>
    0.36
     main
    0.36
    autical
    0.36
    çar
    0.35
    Activations Density 0.000%

    No Known Activations