© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    a combination of opinion words, technical programming terms, and sentence fragments

    oai_token-act-pair · gemini-2.0-flash

    Code/opinion with degree

    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
    выше
    -0.46
     ogóle
    -0.45
     gimana
    -0.44
     enggak
    -0.44
    komt
    -0.43
    tissage
    -0.43
     parteci
    -0.42
     dampak
    -0.42
     rispet
    -0.42
    ároz
    -0.42
    POSITIVE LOGITS
    AccessorTable
    0.76
     amused
    0.71
    ագրություններ
    0.70
    TagMode
    0.69
    XmlAccessorType
    0.68
     himo
    0.68
     amusing
    0.66
     volon
    0.66
     архивлан
    0.64
     nahilalakip
    0.64
    Activations Density 4.368%

    No Known Activations