© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180254
    Prev
    Next
    INDEX
    Explanations

    leads to

    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_29_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
    ͘
    0.37
    fake
    0.37
    geq
    0.34
     fighter
    0.34
    marine
    0.33
     cate
    0.33
    display
    0.32
     चुकी
    0.32
    jena
    0.32
    iget
    0.32
    POSITIVE LOGITS
    上升
    0.36
    䄳
    0.36
    utivo
    0.36
     افس
    0.35
    丝
    0.35
     eficaz
    0.35
     difícil
    0.34
     разговор
    0.34
    孤独
    0.34
    ູນ
    0.34
    Activations Density 0.008%

    No Known Activations