© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76717
    Prev
    Next
    INDEX
    Explanations

    years days months hours

    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_31_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
     reprise
    0.35
    ⼦
    0.29
     شیطان
    0.29
     Intro
    0.28
     rightly
    0.28
     visão
    0.28
     didSet
    0.28
    arnya
    0.27
    Rat
    0.27
    颉
    0.27
    POSITIVE LOGITS
    ]?
    0.29
    ීන්
    0.28
     تجاه
    0.27
     drove
    0.27
     लिखिए
    0.27
    ServiceClient
    0.27
    扩展
    0.27
    uchtigkeit
    0.27
    려서
    0.27
    滲
    0.26
    Activations Density 0.004%

    No Known Activations