© 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. 14320
    Prev
    Next
    INDEX
    Explanations

    references to studies and quantities/measurements, and the words that link them

    oai_token-act-pair · gemini-2.0-flash

    Scientific writing

    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
    FormTagHelper
    -0.72
    HideFlags
    -0.63
    SequentialGroup
    -0.62
    كويكب
    -0.60
    IsContent
    -0.57
     Italijani
    -0.57
     abstrait
    -0.55
     hoort
    -0.55
    SdkVersion
    -0.53
     onOptions
    -0.52
    POSITIVE LOGITS
    ومة
    0.46
     AM
    0.46
    posedge
    0.46
    Rptr
    0.45
     produced
    0.45
    mingen
    0.44
     covered
    0.43
    MockMvc
    0.43
     degree
    0.42
     schne
    0.42
    Activations Density 3.515%

    No Known Activations