© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10721
    Prev
    Next
    INDEX
    Explanations

    specific alphanumeric codes or lab designations

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     objectForKey
    -0.52
    FormTagHelper
    -0.50
    principalColumn
    -0.49
    っこう
    -0.49
     européens
    -0.48
     élas
    -0.47
     véritables
    -0.46
     bords
    -0.46
     élevés
    -0.46
    uß
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.57
    Rhestr
    0.52
    UnusedPrivate
    0.50
     تانيه
    0.48
    PYX
    0.48
    tonode
    0.47
    Życiorys
    0.47
    clearpage
    0.47
    SequentialGroup
    0.46
     INTERESAR
    0.46
    Activations Density 5.313%

    No Known Activations