© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5313
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic funding, grants, and fellowships

    oai_token-act-pair · gemini-2.0-flash

    Fellowships and awards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     msglen
    -0.52
     дописавши
    -0.49
    éraire
    -0.48
     LUMP
    -0.47
    InvalidProtocol
    -0.45
     onCreateView
    -0.45
    ECTS
    -0.44
    тивов
    -0.44
    moveToFirst
    -0.43
    apper
    -0.43
    POSITIVE LOGITS
     fellowship
    0.91
     fellowships
    0.82
     fellows
    0.77
     Fellowship
    0.73
     Fulbright
    0.69
     Visiting
    0.68
     FELLOW
    0.68
    fellow
    0.63
     Normdatei
    0.61
     visiting
    0.60
    Activations Density 1.323%

    No Known Activations