© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4255
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    oai_token-act-pair · gemini-2.0-flash

    multilingual content or formatting terms

    np_token-act-pair-logits · gpt-4o-mini

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagHelperRunner
    -0.79
    んぼ
    -0.57
     AssemblyVersion
    -0.54
    copyOf
    -0.52
    ftagPool
    -0.50
    hpur
    -0.49
    Espèce
    -0.48
    ритори
    -0.48
    
    -0.48
    nloa
    -0.47
    POSITIVE LOGITS
    contentLoaded
    0.60
     judiciaire
    0.58
     féminine
    0.57
    FieldOffset
    0.56
     دیکھیے
    0.56
     SqlDbType
    0.54
    Revenir
    0.53
    Наводи
    0.51
     AssemblyTitle
    0.50
    География
    0.50
    Activations Density 1.136%

    No Known Activations