© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11738
    Prev
    Next
    INDEX
    Explanations

    words related to statements of giving or stating.

    oai_token-act-pair · gemini-2.0-flash

    define, provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     simulate
    -1.30
     imitate
    -1.26
     motivate
    -1.25
     optimise
    -1.23
     simplify
    -1.23
     rehabilitate
    -1.23
     organise
    -1.22
     regulate
    -1.22
     migrate
    -1.22
     improve
    -1.21
    POSITIVE LOGITS
    <bos>
    1.13
     the
    0.76
     one
    0.69
     a
    0.68
     most
    0.64
     vast
    0.64
     two
    0.63
     given
    0.63
     more
    0.62
     first
    0.61
    Activations Density 2.131%

    No Known Activations