© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13914
    Prev
    Next
    INDEX
    Explanations

    what appears to be scientific data references, including numbers, and abbreviations in parentheses

    oai_token-act-pair · gemini-2.0-flash

    code/data addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     propOrder
    -0.57
    oredCriteria
    -0.53
     Roskov
    -0.51
    TypedDataSet
    -0.48
     Waray
    -0.46
     kasarigan
    -0.46
    fjspx
    -0.45
    __*/
    -0.45
    XmlAccessorType
    -0.45
     EconPapers
    -0.44
    POSITIVE LOGITS
    BGP
    0.57
    BPF
    0.56
    PSO
    0.56
    Legături
    0.55
     CEA
    0.53
    TGA
    0.53
     BPS
    0.52
    GPR
    0.51
    TPS
    0.51
    CNP
    0.51
    Activations Density 23.350%

    No Known Activations