© 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. 157117
    Prev
    Next
    INDEX
    Explanations

    technology and projects

    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
     सभ्यता
    0.45
     दृ
    0.38
    PathParam
    0.38
     Free
    0.37
     Accountability
    0.37
     Needham
    0.37
    安倍
    0.37
    皖
    0.37
     Cobb
    0.36
    த்திலிருந்து
    0.36
    POSITIVE LOGITS
     reiniciar
    0.42
    плуа
    0.38
     Grau
    0.37
     split
    0.37
     Jh
    0.37
     pausa
    0.37
     fh
    0.36
     ZH
    0.36
     parcour
    0.36
     derecha
    0.35
    Activations Density 0.004%

    No Known Activations