© 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. 139508
    Prev
    Next
    INDEX
    Explanations

    combination figure

    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
    ትክል
    0.42
    釗
    0.42
     किल्ल्या
    0.40
    джи
    0.39
     நெடு
    0.39
    basecode
    0.39
     Антон
    0.39
     बच्चन
    0.39
    MenuInflater
    0.38
     Балт
    0.38
    POSITIVE LOGITS
     combinación
    0.40
     ጥ
    0.39
     movimiento
    0.38
    ಶ
    0.38
     Detalles
    0.38
     PTO
    0.37
    瓢
    0.37
     figura
    0.37
     estrella
    0.37
    otá
    0.36
    Activations Density 0.004%

    No Known Activations