© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 157555
    Prev
    Next
    INDEX
    Explanations

    header

    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
    bene
    0.45
    ेशन
    0.43
    legenheit
    0.41
    ABET
    0.39
    itives
    0.38
    <0xB7>
    0.38
    átil
    0.38
    éter
    0.37
    àn
    0.37
    મિંગ
    0.37
    POSITIVE LOGITS
    雵
    0.42
     CAC
    0.40
     kre
    0.39
     opa
    0.39
     astrophys
    0.38
     pilha
    0.38
    吘
    0.38
     cobbl
    0.37
     hears
    0.37
    ッキー
    0.37
    Activations Density 0.003%

    No Known Activations