© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8896
    Prev
    Next
    INDEX
    Explanations

    the word "lots" and sometimes also finds words like "abundance"

    oai_token-act-pair · gemini-2.0-flash

    lots

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     esternos
    -0.89
    Vidite
    -0.81
    WithMany
    -0.79
    OGND
    -0.74
     Paglinawan
    -0.73
    setVerticalGroup
    -0.70
    SuspendLayout
    -0.69
    HasForeignKey
    -0.69
     []:
    -0.68
     defStyle
    -0.68
    POSITIVE LOGITS
    ு
    0.47
    passt
    0.46
    ニ
    0.40
    fast
    0.39
    vo
    0.39
    ilog
    0.38
    最快更新
    0.38
     actually
    0.37
     available
    0.37
    full
    0.37
    Activations Density 0.497%

    No Known Activations