© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9888
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical calculations and measurements

    oai_token-act-pair · gemini-2.0-flash

    calculated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     المعيارى
    -0.75
     femininas
    -0.65
    enumii
    -0.60
     ProtoMessage
    -0.59
    chanel
    -0.57
    DockStyle
    -0.57
    ageo
    -0.56
     femininos
    -0.56
     Photocase
    -0.54
    balleur
    -0.54
    POSITIVE LOGITS
     multiply
    0.65
     Multiply
    0.59
     multip
    0.58
     multiplied
    0.51
     multiplication
    0.51
     multiplying
    0.51
     ratios
    0.50
     average
    0.50
     ratio
    0.50
    multiply
    0.49
    Activations Density 28.207%

    No Known Activations