© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9650
    Prev
    Next
    INDEX
    Explanations

    words related to technology, particularly emphasizing solutions, connections, features, and alternative methods.

    oai_token-act-pair · gemini-2.0-flash

    solutions or advantages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     MenuView
    -0.51
     Eins
    -0.46
    RICAL
    -0.45
    matorium
    -0.45
     Sis
    -0.44
    tholes
    -0.44
    raga
    -0.44
    ఞ
    -0.43
    alea
    -0.43
    AllAfrica
    -0.43
    POSITIVE LOGITS
     AssemblyVersion
    0.83
    Tembelea
    0.80
     TestBed
    0.80
     nahilalakip
    0.72
     الحره
    0.69
    __(/*!
    0.69
    ंदीखरीदारी
    0.68
     transfieras
    0.66
    IntoConstraints
    0.65
     commerciali
    0.62
    Activations Density 6.423%

    No Known Activations