© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132164
    Prev
    Next
    INDEX
    Explanations

    models

    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_50_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
    टीसी
    0.44
     MST
    0.42
    IOR
    0.41
    IST
    0.41
    驄
    0.41
     TI
    0.39
     aussitôt
    0.39
    ეხ
    0.38
     MHK
    0.38
     SONS
    0.38
    POSITIVE LOGITS
    <0x84>
    0.43
     الل
    0.38
     Л
    0.37
    ²
    0.37
    𝑳
    0.37
    ʟ
    0.37
     *
    0.36
    LR
    0.36
    𝗟
    0.36
    Ler
    0.36
    Activations Density 0.012%

    No Known Activations