© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15254
    Prev
    Next
    INDEX
    Explanations

    words related to geography and genomics

    oai_token-act-pair · gemini-2.0-flash

    latitude/parallel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    $+\
    -0.66
    Autoritní
    -0.64
    Literatura
    -0.59
    IContainer
    -0.57
    grà
    -0.54
    frastructure
    -0.51
    keletal
    -0.51
     Remark
    -0.51
    rawDesc
    -0.51
     cherchés
    -0.50
    POSITIVE LOGITS
    fromnode
    0.73
    uxxxx
    0.59
     للاسماء
    0.57
    ArgsConstructor
    0.56
    SizeMode
    0.54
    Parcelize
    0.53
     varandra
    0.52
    fillType
    0.51
    URLException
    0.50
     död
    0.50
    Activations Density 2.363%

    No Known Activations