© 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. 214851
    Prev
    Next
    INDEX
    Explanations

    National institutions

    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
     น
    0.41
    chae
    0.39
     Tutor
    0.39
    Ku
    0.39
    кура
    0.39
     تخ
    0.38
    ارہ
    0.38
    蒴
    0.38
     দূরত্ব
    0.37
     Donovan
    0.37
    POSITIVE LOGITS
     segunda
    0.37
    default
    0.36
    మ్ము
    0.36
    Default
    0.35
     probabil
    0.35
    朦
    0.34
    즈
    0.33
     default
    0.33
     =\
    0.33
     demasi
    0.33
    Activations Density 0.001%

    No Known Activations