© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15217
    Prev
    Next
    INDEX
    Explanations

    the acronym GL

    oai_token-act-pair · gemini-2.0-flash

    Hall, GL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     BrowserModule
    -0.68
    :✨
    -0.67
    amis
    -0.60
    __(/*!
    -0.59
     plat
    -0.59
     (
    -0.59
     Gran
    -0.58
     Gar
    -0.58
    ertion
    -0.58
    "",
    -0.56
    POSITIVE LOGITS
    <bos>
    2.44
     myſelf
    1.02
     itſelf
    0.95
     themſelves
    0.93
     Monfieur
    0.93
     Cæsar
    0.90
     Jefus
    0.90
     pleaſure
    0.85
     Shakspeare
    0.85
     Efq
    0.84
    Activations Density 1.386%

    No Known Activations