© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9756
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in academic research papers

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    IsContent
    -0.84
     insuffisamment
    -0.75
     AssemblyProduct
    -0.72
    LabelTagHelper
    -0.65
    HomeAsUpEnabled
    -0.59
    kmäler
    -0.59
    tagHelperRunner
    -0.57
    EndInit
    -0.57
     كومونز
    -0.56
    newtheorem
    -0.56
    POSITIVE LOGITS
    -
    0.60
     kvar
    0.52
     gouttes
    0.51
    sizeCache
    0.49
     consolidated
    0.47
     kullanılır
    0.47
    Rcpp
    0.47
     valgt
    0.47
    oredCriteria
    0.47
     mulighed
    0.46
    Activations Density 4.328%

    No Known Activations