© 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. 13902
    Prev
    Next
    INDEX
    Explanations

    various words and symbols of technical and academic writing

    oai_token-act-pair · gemini-2.0-flash

    green party/color

    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
     AssemblyTitle
    -0.59
     kasarigan
    -0.57
    WriteTagHelper
    -0.56
     rarest
    -0.55
     calendriers
    -0.50
     Shut
    -0.50
    __':
    -0.50
    buttonShape
    -0.50
    
    -0.49
     MainAxisSize
    -0.49
    POSITIVE LOGITS
    bootstrapcdn
    0.80
    fortawesome
    0.57
     classique
    0.56
     transférez
    0.54
     ordinaire
    0.54
     normale
    0.54
     ordinaria
    0.53
     ordinario
    0.53
     traditionnelle
    0.53
     일반
    0.53
    Activations Density 4.075%

    No Known Activations