© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9749
    Prev
    Next
    INDEX
    Explanations

    conjunctions, especially "but", "and", and words related to time like now/when

    oai_token-act-pair · gemini-2.0-flash

    conjunctions/discourse markers

    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
     Dumnezeu
    -0.65
     littéraire
    -0.60
     pyrite
    -0.60
     canst
    -0.60
     Muf
    -0.59
     plagioclase
    -0.59
     hemispheres
    -0.57
    odoro
    -0.56
     biotite
    -0.56
     hindurch
    -0.56
    POSITIVE LOGITS
    <bos>
    1.06
     Infórmanos
    0.52
     AssemblyCulture
    0.52
    titleMargin
    0.48
     noted
    0.47
    gouv
    0.47
     beginnetje
    0.46
    ‍♂️
    0.46
     cellspacing
    0.46
     then
    0.46
    Activations Density 1.642%

    No Known Activations