© 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. 8933
    Prev
    Next
    INDEX
    Explanations

    the word 'a' preceded by words indicating a description or contrast

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     useAppContext
    -0.79
     betweenstory
    -0.78
     GenerationType
    -0.77
    OGND
    -0.75
     ujednoznacz
    -0.73
    ErrUnexpectedEOF
    -0.69
    DoubleQuotes
    -0.68
     oprot
    -0.65
    PhysRev
    -0.65
     HasFactory
    -0.65
    POSITIVE LOGITS
    till
    0.48
     specific
    0.48
     single
    0.45
    toBe
    0.45
    tilli
    0.44
    tol
    0.44
    imir
    0.44
    VING
    0.43
     very
    0.42
     small
    0.42
    Activations Density 1.306%

    No Known Activations