© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2391
    Prev
    Next
    INDEX
    Explanations

    times written in the format of a number followed by a colon and then a number, and ending with "a.m." or "p.m."

    oai_token-act-pair · gemini-2.0-flash

    p

    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
    存于互联网档案馆
    -0.84
     مشين
    -0.64
     &___
    -0.64
     calendriers
    -0.62
    SharedCtor
    -0.61
    CloseOperation
    -0.59
    $_['
    -0.59
    évaluateur
    -0.59
    resave
    -0.58
    KommentareTeilen
    -0.57
    POSITIVE LOGITS
    бур
    0.51
    Ô
    0.51
    noy
    0.50
    naw
    0.49
    halb
    0.48
    inação
    0.47
    нской
    0.47
    нская
    0.47
    use
    0.46
    tă
    0.46
    Activations Density 0.963%

    No Known Activations