© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4883
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to scientific analysis, experiments, and technical results

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Fer
    -0.58
    Fer
    -0.57
    ano
    -0.56
    Tu
    -0.53
    ]=-
    -0.52
     själ
    -0.50
    fer
    -0.50
     tu
    -0.49
    ума
    -0.47
     Tu
    -0.47
    POSITIVE LOGITS
    WindowConstants
    0.66
    脚注の使い方
    0.64
    tonode
    0.59
    pexpr
    0.57
     SqlDbType
    0.57
    ására
    0.57
    Transcripción
    0.56
     propOrder
    0.56
    BeginContext
    0.55
    IntoConstraints
    0.55
    Activations Density 12.279%

    No Known Activations