© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 80270
    Prev
    Next
    INDEX
    Explanations

    DIN

    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
     Naval
    0.43
     luis
    0.41
    hig
    0.41
     sail
    0.41
     Go
    0.41
     p
    0.40
    Sail
    0.40
    โก
    0.39
     l
    0.39
     cardiaque
    0.39
    POSITIVE LOGITS
    枃
    0.47
     बाबर
    0.42
     degeneration
    0.39
     Bab
    0.39
    हट
    0.38
    ಡುವ
    0.38
    utt
    0.38
    ణా
    0.37
    stringify
    0.37
    bab
    0.37
    Activations Density 0.000%

    No Known Activations