© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5593
    Prev
    Next
    INDEX
    Explanations

    terms related to debugging a program or using developer tools, as well as references to years and statistics.

    oai_token-act-pair · gemini-2.0-flash

    data analysis and summaries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Життєпис
    -0.66
     poffible
    -0.64
     يتيمه
    -0.64
     fhort
    -0.64
     whoſe
    -0.62
    ạng
    -0.62
     myſelf
    -0.62
    sidemargin
    -0.61
    SourceChecksum
    -0.61
     betweenstory
    -0.60
    POSITIVE LOGITS
     heat
    0.46
    AddTagHelper
    0.44
    HttpDelete
    0.43
     AssemblyCulture
    0.42
     reports
    0.42
    oxane
    0.41
    zzar
    0.41
    ivo
    0.41
     cracks
    0.40
     Builder
    0.40
    Activations Density 12.438%

    No Known Activations