© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12429
    Prev
    Next
    INDEX
    Explanations

    phrases involving future tense, speculation, or planning

    oai_token-act-pair · gemini-2.0-flash

    going to happen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     will
    -1.23
    will
    -1.05
    Will
    -0.94
     gonna
    -0.85
     WILL
    -0.84
     Will
    -0.84
     shall
    -0.82
     akan
    -0.81
     fhall
    -0.80
     sẽ
    -0.79
    POSITIVE LOGITS
    
    0.68
    inSlope
    0.65
     AssemblyProduct
    0.62
     فريبيس
    0.59
     ISNI
    0.55
    ::_('
    0.52
    MetaObject
    0.52
     EdgeInsets
    0.52
     BIBSYS
    0.51
    TintMode
    0.51
    Activations Density 0.501%

    No Known Activations