© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 237
    Prev
    Next
    INDEX
    Explanations

    sentences describing something, including its composition, purpose, and history.

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    цездатний
    -0.90
     lenker
    -0.88
    — 
    -0.83
     defaultstate
    -0.80
    Hentet
    -0.77
    InputBorder
    -0.75
     kanssa
    -0.75
    قایناقلار
    -0.75
     Приступљено
    -0.74
    posedge
    -0.73
    POSITIVE LOGITS
     said
    0.59
     most
    0.59
    oty
    0.59
    k
    0.50
    ken
    0.48
     when
    0.46
    most
    0.45
    Most
    0.45
    zhi
    0.44
     الشم
    0.44
    Activations Density 4.557%

    No Known Activations