© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4537
    Prev
    Next
    INDEX
    Explanations

    mentions of area, especially with numeric values

    oai_token-act-pair · gemini-2.0-flash

    specific numerical data and area measurements

    np_token-act-pair-logits · gpt-4o-mini

    Units of area

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    afficheront
    -0.67
    évaluateur
    -0.66
     RSSSF
    -0.61
    numerusform
    -0.57
    ynchronously
    -0.56
    vably
    -0.54
    HasIndex
    -0.53
    SBATCH
    -0.53
    Atsauces
    -0.52
    FormBuilder
    -0.52
    POSITIVE LOGITS
    出版年
    0.54
    Domain
    0.53
     sell
    0.52
    Ligações
    0.50
     المعيارى
    0.49
    цездатний
    0.48
     sells
    0.47
    icor
    0.47
    html
    0.46
    gate
    0.46
    Activations Density 2.761%

    No Known Activations