© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6873
    Prev
    Next
    INDEX
    Explanations

    words related to the action of scientific investigation and discovery, especially where several elements are working in tandem

    oai_token-act-pair · gemini-2.0-flash

    Research/technical papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     AssemblyProduct
    -0.61
    AxisAlignment
    -0.57
    SBATCH
    -0.55
    argout
    -0.55
    wili
    -0.52
    forName
    -0.48
     Joi
    -0.47
    webElementGuid
    -0.47
     typelib
    -0.47
     Hau
    -0.45
    POSITIVE LOGITS
    ]]]
    0.63
    EReference
    0.62
    ']))
    0.60
    واعد
    0.60
    "]];
    0.58
    "))
    0.58
    "]))
    0.56
     resourceCulture
    0.54
    UnusedPrivate
    0.54
    cyjna
    0.54
    Activations Density 3.186%

    No Known Activations