© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10114
    Prev
    Next
    INDEX
    Explanations

    the prefix "reg" in words, but also sometimes the contraction "isn't" and the word "charges"

    oai_token-act-pair · gemini-2.0-flash

    Charges, auto-regression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     مشين
    -1.20
    RenderAtEndOf
    -0.93
     Meksiku
    -0.91
    fromnode
    -0.83
    abestanden
    -0.82
    EndProject
    -0.82
    makeConstraints
    -0.82
    kloped
    -0.82
    ReusableCell
    -0.81
     beginnetje
    -0.80
    POSITIVE LOGITS
     either
    0.71
    ,
    0.71
     her
    0.62
     an
    0.60
     both
    0.60
     the
    0.59
     ultimately
    0.58
     a
    0.57
     otherwise
    0.51
     in
    0.50
    Activations Density 1.980%

    No Known Activations