© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80569
    Prev
    Next
    INDEX
    Explanations

    German words

    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_53_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
     Re
    0.44
     ሽፋ
    0.42
     Be
    0.39
     Stand
    0.39
     স্বপ
    0.39
     Лей
    0.38
    급
    0.37
     ማስ
    0.37
    幌
    0.37
    Plots
    0.37
    POSITIVE LOGITS
    पि
    0.39
     speck
    0.37
     যৌথ
    0.36
     Wah
    0.35
     sarà
    0.34
    <0x99>
    0.34
    ahuasca
    0.33
     मैन
    0.33
     ಓ
    0.33
     맨
    0.33
    Activations Density 0.005%

    No Known Activations