© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9768
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe a low price

    oai_token-act-pair · gemini-2.0-flash

    Prices and value

    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
    ########.
    -0.94
    Datuak
    -0.79
    UserScript
    -0.78
     ujednoznacz
    -0.77
    rungsseite
    -0.71
    tagHelperRunner
    -0.68
    новниш
    -0.68
     Biôgrafia
    -0.66
    بوابة
    -0.65
    TypedDataSet
    -0.65
    POSITIVE LOGITS
    ap
    0.46
    Insufficient
    0.41
     lamang
    0.40
     ApiResponse
    0.40
    semantics
    0.40
    forChild
    0.40
    لد
    0.39
    ۪
    0.38
     alpina
    0.38
    unlikely
    0.37
    Activations Density 0.195%

    No Known Activations