© 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. 9805
    Prev
    Next
    INDEX
    Explanations

    code snippets, examples showing how things work, and associated terms

    oai_token-act-pair · gemini-2.0-flash

    code examples and documentation

    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
    ConstraintMaker
    -1.17
     '\\;'
    -1.09
    parsedMessage
    -0.96
     ddelweddau
    -0.95
    InputBorder
    -0.94
    OGND
    -0.94
     Monfieur
    -0.94
     Efq
    -0.93
    #+#
    -0.92
     Мексичка
    -0.89
    POSITIVE LOGITS
    <eos>
    0.52
     t
    0.47
     
    0.45
     full
    0.43
    ...
    0.43
     T
    0.42
     tar
    0.42
    :
    0.42
     col
    0.41
    full
    0.41
    Activations Density 1.191%

    No Known Activations