© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13318
    Prev
    Next
    INDEX
    Explanations

    the word "general," sometimes followed by a suffix

    oai_token-act-pair · gemini-2.0-flash

    general

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     general
    -2.77
    general
    -2.45
    General
    -2.34
     General
    -2.33
     GENERAL
    -2.09
    GENERAL
    -2.00
     général
    -1.82
     generale
    -1.55
     generales
    -1.54
     generali
    -1.48
    POSITIVE LOGITS
    rungsseite
    0.92
     AssemblyCulture
    0.81
     &___
    0.78
    PhysRev
    0.72
    TagMode
    0.69
    ophones
    0.69
    rsiniz
    0.68
    Demografia
    0.68
    Cyfeiriadau
    0.66
    aVar
    0.64
    Activations Density 0.537%

    No Known Activations