© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9943
    Prev
    Next
    INDEX
    Explanations

    information about radio stations

    oai_token-act-pair · gemini-2.0-flash

    broadcasting/news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ligiloj
    -0.60
    StoryboardSegue
    -0.59
    RegressionTest
    -0.58
    ScopeManager
    -0.55
     $__
    -0.54
    rungsseite
    -0.54
    .$_
    -0.54
     hefyd
    -0.52
     Waray
    -0.50
    脚注の使い方
    -0.49
    POSITIVE LOGITS
     незавершена
    0.50
    pede
    0.49
    SourceChecksum
    0.48
    سطس
    0.47
     '\\;'
    0.45
     Merv
    0.44
     Melville
    0.44
    텝
    0.44
    igraph
    0.43
    âme
    0.43
    Activations Density 0.462%

    No Known Activations