© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139150
    Prev
    Next
    INDEX
    Explanations

    names/entities

    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_46_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
     gost
    0.39
     Lik
    0.37
     xvii
    0.37
     Keb
    0.37
    başı
    0.37
     تیس
    0.37
    슴
    0.36
     Corn
    0.35
    ফের
    0.35
    chromedriver
    0.35
    POSITIVE LOGITS
    REM
    0.45
    Alliance
    0.43
    泡
    0.39
     alliance
    0.38
    Ion
    0.38
    Arr
    0.37
    Allen
    0.37
     Alliance
    0.36
    联盟
    0.36
     FOR
    0.36
    Activations Density 0.008%

    No Known Activations