© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6817
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by past tense verbs

    oai_token-act-pair · gemini-2.0-flash

    Code/programming related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Initially
    -1.23
     initially
    -1.13
    Initially
    -1.12
     inicialmente
    -0.93
     anfangs
    -0.86
     Initial
    -0.81
    Initial
    -0.79
     initial
    -0.79
     awalnya
    -0.78
    最初は
    -0.75
    POSITIVE LOGITS
     viewDidLoad
    0.69
     resourceCulture
    0.67
     crossorigin
    0.67
     مرئيه
    0.67
    !*\
    0.67
    ubehör
    0.65
    RenderAtEndOf
    0.63
     الرياضيه
    0.63
    Lähteet
    0.63
     DriverManager
    0.63
    Activations Density 7.115%

    No Known Activations