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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10141
    Prev
    Next
    INDEX
    Explanations

    the number one and other numbers

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     كومونز
    -0.85
    LabelTagHelper
    -0.72
    Personensuche
    -0.70
    новниш
    -0.69
    CppMethod
    -0.69
     NSCoder
    -0.67
    ništ
    -0.66
    FormTagHelper
    -0.65
     Paglinawan
    -0.64
    makeConstraints
    -0.63
    POSITIVE LOGITS
    1
    0.88
     lucru
    0.50
     Compton
    0.50
     Castilla
    0.47
     Things
    0.47
    Things
    0.46
     bellezza
    0.45
    Yes
    0.45
     drá
    0.42
    yes
    0.41
    Activations Density 3.309%

    No Known Activations