© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14292
    Prev
    Next
    INDEX
    Explanations

    the word "pure" and HTML formatting code

    oai_token-act-pair · gemini-2.0-flash

    pure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pure
    -3.09
     Pure
    -2.98
    Pure
    -2.89
    pure
    -2.77
     PURE
    -2.61
    PURE
    -2.36
     puro
    -2.02
     purity
    -1.92
     purer
    -1.91
     pura
    -1.90
    POSITIVE LOGITS
    p
    0.68
     IBOutlet
    0.57
     mellitus
    0.57
    ांक
    0.53
     gră
    0.52
     جغرافيا
    0.52
     AssemblyProduct
    0.51
     AllAfrica
    0.50
    bestos
    0.49
    WithIOException
    0.49
    Activations Density 3.889%

    No Known Activations