© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16244
    Prev
    Next
    INDEX
    Explanations

    the prefix "pri" usually found at the beginning of Russian or Croatian words

    oai_token-act-pair · gemini-2.0-flash

    pri

    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
    +:+
    -0.76
     initComponents
    -0.71
    WriteTagHelper
    -0.67
    AntiForgeryToken
    -0.66
    KURZBESCHREIBUNG
    -0.66
    żeń
    -0.63
     Winaray
    -0.62
     }}"></
    -0.62
     impunity
    -0.61
    HtmlAttribute
    -0.61
    POSITIVE LOGITS
     مواليد
    0.57
     semula
    0.48
    thums
    0.47
    Double
    0.46
    enu
    0.46
     termica
    0.45
     profondeur
    0.45
     double
    0.45
    double
    0.44
     straight
    0.44
    Activations Density 0.426%

    No Known Activations