© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10660
    Prev
    Next
    INDEX
    Explanations

    code with words used in programming such as "boost", "tuple", "code", "@return", "list", and "from"

    oai_token-act-pair · gemini-2.0-flash

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.74
    from
    -0.58
    to
    -0.54
    for
    -0.51
     p
    -0.50
    with
    -0.47
     M
    -0.45
     n
    -0.42
     join
    -0.41
     k
    -0.40
    POSITIVE LOGITS
     Efq
    0.98
     itſelf
    0.95
     Theſe
    0.94
    
    0.89
     himſelf
    0.89
    reactstrap
    0.87
    tvguidetime
    0.86
     themſelves
    0.85
     Reſ
    0.85
     myſelf
    0.85
    Activations Density 17.467%

    No Known Activations