© 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. 14026
    Prev
    Next
    INDEX
    Explanations

    the word "in" preceded or proceeded by particular words or punctuation, often related to scope or scale

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    يكب
    -0.50
    しくは
    -0.49
    seamnă
    -0.49
    visející
    -0.48
    riwal
    -0.48
     onCreateView
    -0.47
    těte
    -0.43
    Do
    -0.41
    ודש
    -0.41
    libft
    -0.40
    POSITIVE LOGITS
    WriteTagHelper
    0.72
     autorytatywna
    0.63
     numerus
    0.61
    Estar
    0.60
     AssemblyProduct
    0.60
     PLWABN
    0.60
    RegressionTest
    0.60
    nloa
    0.59
    AccessorTable
    0.59
    تقاوى
    0.59
    Activations Density 4.719%

    No Known Activations