© 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. 10496
    Prev
    Next
    INDEX
    Explanations

    hyphens, underscores, and code-related keywords such as probes, with, install, python, tap and dtrace.

    oai_token-act-pair · gemini-2.0-flash

    dashes/underscores

    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
     ComVisible
    -0.67
    genheim
    -0.66
    StoreMessageInfo
    -0.65
     Pelop
    -0.63
     Vikipedi
    -0.62
     typelib
    -0.62
     hasbro
    -0.61
     Audiodateien
    -0.61
    Tarih
    -0.61
    Obrázky
    -0.60
    POSITIVE LOGITS
    <bos>
    0.96
    httphttps
    0.69
     the
    0.58
     a
    0.51
     what
    0.50
     its
    0.48
     served
    0.47
     serves
    0.46
     to
    0.46
     some
    0.45
    Activations Density 3.798%

    No Known Activations