© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39410
    Prev
    Next
    INDEX
    Explanations

    G

    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_57_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
    Incorpor
    0.41
    lede
    0.40
    Historically
    0.38
    нений
    0.38
    됨
    0.37
    PSS
    0.37
    developed
    0.37
     embeds
    0.36
    incorpor
    0.36
    otor
    0.36
    POSITIVE LOGITS
    ροι
    0.43
     बाँ
    0.42
    ственную
    0.39
     endIndex
    0.39
    論
    0.38
    釗
    0.38
    বিজ্ঞ
    0.38
     est
    0.38
     duke
    0.38
    anh
    0.37
    Activations Density 0.008%

    No Known Activations