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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15023
    Prev
    Next
    INDEX
    Explanations

    a mix of discourse-related words, technical terms, legal speak and interjections, suggesting it is finding the connective tissue in an argument or explanation.

    oai_token-act-pair · gemini-2.0-flash

    Arguments and claims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    IsContent
    -0.70
    脚注の使い方
    -0.65
     pinulongan
    -0.59
     يتيمه
    -0.57
    véni
    -0.56
    RegistryLite
    -0.56
    enderror
    -0.54
    writeFieldEnd
    -0.53
    =$?
    -0.53
     tục
    -0.52
    POSITIVE LOGITS
     kaynağından
    0.73
     heapq
    0.57
    يميديا
    0.56
     Référence
    0.54
    Revenir
    0.54
     transférez
    0.51
     useParams
    0.51
     ClassNotFound
    0.50
     atve
    0.50
     Ambition
    0.50
    Activations Density 21.175%

    No Known Activations