© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 852
    Prev
    Next
    INDEX
    Explanations

    hyphenated words that have some relationship to "state of the art", Wi-Fi or a television.

    oai_token-act-pair · gemini-2.0-flash

    of, built, by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AsUp
    -0.62
     Infórmanos
    -0.60
    kloped
    -0.54
     autorytatywna
    -0.54
     SqlParameter
    -0.54
    iconque
    -0.54
    ="?
    -0.53
    ()].
    -0.53
     незавершена
    -0.52
     noqa
    -0.51
    POSITIVE LOGITS
    躇
    0.71
    Lähteet
    0.64
     noten
    0.60
    出版年
    0.59
    findpost
    0.58
    ReusableCell
    0.56
     cref
    0.54
    Rptr
    0.53
    Referències
    0.52
    urai
    0.51
    Activations Density 4.975%

    No Known Activations