© 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. 198482
    Prev
    Next
    INDEX
    Explanations

    people and names

    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
     올
    0.41
     kriv
    0.40
     право
    0.40
     humedad
    0.39
     конвер
    0.39
     discapacidad
    0.39
    Madam
    0.38
     Kana
    0.38
    𝑭
    0.38
     मातरम
    0.37
    POSITIVE LOGITS
     oysters
    0.38
    Theta
    0.38
    ਰਾ
    0.38
     indefin
    0.38
    ْت
    0.37
    ਲੇ
    0.37
     lo
    0.37
    ümü
    0.37
     mnemonic
    0.37
     thymus
    0.37
    Activations Density 0.000%

    No Known Activations