© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13422
    Prev
    Next
    INDEX
    Explanations

    location names from California and Louisiana along with associated legal or corporate terms, especially those related to Oracle

    oai_token-act-pair · gemini-2.0-flash

    specific technical jargon or formatting identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Technology and named entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ValueStyle
    -0.88
     Normdatei
    -0.78
     <=",
    -0.75
    OrNil
    -0.65
    ItemBackground
    -0.65
     actionMode
    -0.64
     كومونز
    -0.63
    CopyWith
    -0.62
    fjspx
    -0.62
    hljs
    -0.62
    POSITIVE LOGITS
    Metric
    0.45
     usize
    0.44
    ward
    0.44
     Mulher
    0.43
    mtd
    0.42
     des
    0.42
     esterni
    0.42
    .__
    0.42
    <tbody>
    0.42
    uelle
    0.42
    Activations Density 1.180%

    No Known Activations