© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4374
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a unit of measure

    oai_token-act-pair · gemini-2.0-flash

    currency and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    bibinfo
    -0.58
    ilich
    -0.57
     fine
    -0.57
     local
    -0.57
     thousands
    -0.56
    IFORNIA
    -0.54
    ACIONAL
    -0.53
     high
    -0.52
     force
    -0.52
     him
    -0.51
    POSITIVE LOGITS
     sympathize
    0.75
     stencils
    0.69
    contentLoaded
    0.69
    PerformLayout
    0.69
     تضيفلها
    0.68
    ftagPool
    0.66
     circums
    0.66
     comigo
    0.65
     XNUMX
    0.65
     alfabe
    0.65
    Activations Density 3.509%

    No Known Activations