© 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. 9786
    Prev
    Next
    INDEX
    Explanations

    words related to technical installation instructions, as well as scientific research text, including numbers in parentheses and references to figures

    oai_token-act-pair · gemini-2.0-flash

    partial, incomplete

    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
    новниш
    -0.64
     garda
    -0.63
    usepackage
    -0.58
     $_"
    -0.57
     Assy
    -0.57
    AndPassword
    -0.57
     DTM
    -0.56
     Sunni
    -0.56
     stiefel
    -0.55
    OCCURRED
    -0.55
    POSITIVE LOGITS
     interim
    0.98
     partial
    0.92
     half
    0.85
     intermediate
    0.84
    partial
    0.82
    intermediate
    0.79
     Half
    0.79
    Partial
    0.77
     Partial
    0.76
     mini
    0.75
    Activations Density 4.925%

    No Known Activations