© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3823
    Prev
    Next
    INDEX
    Explanations

    LaTeX equations with exponents, trigonometric functions, and other mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    Formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     GenerationType
    -0.69
    ExtendWith
    -0.59
    TestingModule
    -0.56
    onAttach
    -0.55
    styleType
    -0.54
    ResponseWriter
    -0.54
    CPtr
    -0.54
    AttributeSet
    -0.53
     otomatig
    -0.49
    monary
    -0.49
    POSITIVE LOGITS
    DockStyle
    0.66
    
    0.59
    }_{
    0.54
     Privacidad
    0.53
    TableAdapter
    0.52
    })_{
    0.50
     *)__
    0.50
    ---*/
    0.49
     teorías
    0.48
    lahraga
    0.47
    Activations Density 4.034%

    No Known Activations