© 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. 10517
    Prev
    Next
    INDEX
    Explanations

    sentences where the speaker is contrasting their experience or opinions with something else, using "we", "I", and forms of "to be."

    oai_token-act-pair · 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
    webElementXpaths
    -0.85
    twimg
    -0.73
     Савезне
    -0.69
    AddTagHelper
    -0.66
    AddHtmlAttribute
    -0.66
    XmlEnum
    -0.63
     VizieR
    -0.63
    addContainerGap
    -0.63
    tonsoft
    -0.61
     CURLOPT
    -0.60
    POSITIVE LOGITS
     مرئيه
    0.44
    Насе
    0.43
    DebuggerStep
    0.43
    fillType
    0.41
     PDI
    0.40
     protest
    0.39
    presto
    0.39
    ifrance
    0.39
     pinulongan
    0.38
    stata
    0.38
    Activations Density 2.264%

    No Known Activations