© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5610
    Prev
    Next
    INDEX
    Explanations

    phrases which are used to explain something.

    oai_token-act-pair · gemini-2.0-flash

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.24
    Geplaatst
    -0.90
    Personensuche
    -0.87
    Билгалдахарш
    -0.83
    aarrggbb
    -0.80
    Personendaten
    -0.79
    Vidite
    -0.78
    kháu
    -0.78
    InjectAttribute
    -0.77
     snippetHide
    -0.77
    POSITIVE LOGITS
     another
    0.50
     viață
    0.49
     continuó
    0.48
     urmă
    0.47
    以下是
    0.47
    intera
    0.47
     bune
    0.46
     desee
    0.46
     tentativo
    0.44
     accomplishments
    0.44
    Activations Density 3.085%

    No Known Activations