© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    questions in the form of "Can someone.." or "Does anyone.." in French

    oai_token-act-pair · gemini-2.0-flash

    one

    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>
    -0.77
    braith
    -0.50
    IContainer
    -0.45
     voľ
    -0.45
     sole
    -0.44
     أق
    -0.44
    """.
    -0.44
    Nosotros
    -0.43
    veja
    -0.43
    "){
    -0.43
    POSITIVE LOGITS
    someone
    1.09
     something
    1.09
     Someone
    1.08
     somebody
    1.07
    Someone
    1.06
     Somebody
    1.05
    somebody
    1.05
     someone
    1.05
     Something
    1.03
    Something
    1.02
    Activations Density 1.036%

    No Known Activations