© 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. 13279
    Prev
    Next
    INDEX
    Explanations

    words that are conjunctions, especially in the immediate context of other words indicating some sort of choice or modification

    oai_token-act-pair · gemini-2.0-flash

    other languages

    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
     Aless
    -0.66
     overturn
    -0.57
     meet
    -0.57
     hire
    -0.56
     penetrate
    -0.55
    ינו
    -0.55
     Inscrivez
    -0.53
     toer
    -0.52
     haunt
    -0.52
     populate
    -0.52
    POSITIVE LOGITS
     lenker
    0.91
    webElementXpaths
    0.85
     كومونز
    0.81
    stateProvider
    0.78
     مرئيه
    0.74
    ReusableCell
    0.74
     препратки
    0.74
    RenderAtEndOf
    0.74
    tanleria
    0.73
     resultCode
    0.73
    Activations Density 3.613%

    No Known Activations