© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12010
    Prev
    Next
    INDEX
    Explanations

    scientific text containing voltage or current measurements of a membrane, channel or bi-layer

    oai_token-act-pair · gemini-2.0-flash

    potential

    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
    ERIES
    -0.49
    WebServlet
    -0.48
    stonia
    -0.45
    ماعة
    -0.43
    ysuckle
    -0.43
    kezés
    -0.43
    rivit
    -0.42
    prototype
    -0.42
    WithMany
    -0.42
     defaultstate
    -0.41
    POSITIVE LOGITS
     potential
    0.72
     potentials
    0.71
     Potential
    0.71
    potential
    0.71
     potenci
    0.70
    Potential
    0.67
     Potenti
    0.65
    期刊论文
    0.63
     poten
    0.62
     POTENTIAL
    0.62
    Activations Density 1.430%

    No Known Activations