© 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. 13656
    Prev
    Next
    INDEX
    Explanations

    code related to data transfer

    oai_token-act-pair · gemini-2.0-flash

    fer

    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
     transferring
    -1.11
     transfer
    -1.11
     Transfer
    -1.10
     transferred
    -1.08
     transfers
    -1.07
     Transfers
    -1.01
    Transfers
    -1.00
     TRANSFER
    -0.98
    transfer
    -0.96
    TRANSFER
    -0.95
    POSITIVE LOGITS
     AssemblyProduct
    0.69
     незавершена
    0.57
    الدراسه
    0.53
     dataSnapshot
    0.51
     mía
    0.46
    ANTLR
    0.46
    出版年
    0.45
     章
    0.44
     politiet
    0.44
     staden
    0.44
    Activations Density 56.708%

    No Known Activations