© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61859
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    imedia
    0.53
    obian
    0.47
    ος
    0.47
    دت
    0.43
    andra
    0.40
    mitter
    0.40
    ि
    0.40
    mitted
    0.39
    pletely
    0.39
     chestnut
    0.38
    POSITIVE LOGITS
    ById
    0.63
    One
    0.63
    ilayer
    0.63
    erness
    0.58
     One
    0.55
    ructive
    0.48
    шен
    0.48
    র
    0.47
    ByUser
    0.47
    ır
    0.45
    Activations Density 0.006%

    No Known Activations