© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11435
    Prev
    Next
    INDEX
    Explanations

    the word "building" or words that can mean construction or adding on to something

    oai_token-act-pair · gemini-2.0-flash

    build

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     building
    -3.16
     Building
    -3.02
    Building
    -2.92
     build
    -2.84
    building
    -2.81
     Build
    -2.77
     builds
    -2.72
    Build
    -2.69
    build
    -2.67
     BUILDING
    -2.66
    POSITIVE LOGITS
    RectangleBorder
    0.71
     <<<<<<<<<<<<<<
    0.64
     Numerade
    0.53
    tagext
    0.51
    PROC
    0.50
    ạng
    0.50
    TargetException
    0.50
     tartalomajánló
    0.49
     Viator
    0.48
     wrink
    0.48
    Activations Density 1.576%

    No Known Activations