© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7703
    Prev
    Next
    INDEX
    Explanations

    emotionally charged arguments related to race and slavery

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    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
    DataURL
    -0.38
    verre
    -0.37
    ophy
    -0.34
     presumption
    -0.33
    ęcia
    -0.32
     stakes
    -0.32
    道理
    -0.31
    台
    -0.31
     Finch
    -0.31
     why
    -0.30
    POSITIVE LOGITS
     صوتيه
    0.96
    AccessorTable
    0.93
     EconPapers
    0.90
    rungsseite
    0.90
     pinulongan
    0.88
    IsContent
    0.88
     الدولى
    0.87
     المعيارى
    0.85
    Datuak
    0.85
    tagHelperRunner
    0.83
    Activations Density 6.506%

    No Known Activations