© 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. 14671
    Prev
    Next
    INDEX
    Explanations

    bits of code that define the edges and nodes of a graph

    oai_token-act-pair · gemini-2.0-flash

    node

    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
    \{\\
    -0.79
     externes
    -0.61
     Autorizaciones
    -0.60
     Zacks
    -0.59
    ########.
    -0.59
    λους
    -0.59
    writeFieldEnd
    -0.59
     AssemblyProduct
    -0.58
     ErrIntOverflow
    -0.58
    ạch
    -0.57
    POSITIVE LOGITS
    extAlignment
    0.63
    aventura
    0.48
     Foire
    0.48
    ToAction
    0.46
    viewBox
    0.46
     Schuld
    0.45
    MISSION
    0.42
    peutic
    0.41
     identifying
    0.41
    DATABASES
    0.41
    Activations Density 3.574%

    No Known Activations