© 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. 15027
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    enyum
    -0.66
     مشين
    -0.60
     Abroad
    -0.59
    〉
    -0.54
    rumah
    -0.52
    nessione
    -0.52
    newArrayList
    -0.51
    spreis
    -0.50
    AGGIO
    -0.50
     strepto
    -0.50
    POSITIVE LOGITS
    ConstraintMaker
    0.71
    <bos>
    0.68
     typelib
    0.66
    ⓧ
    0.66
     defaultstate
    0.61
    ptonshire
    0.60
     Normdatei
    0.60
    WebServlet
    0.60
     Roskov
    0.60
    webElementXpaths
    0.55
    Activations Density 1.484%

    No Known Activations