© 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. 14676
    Prev
    Next
    INDEX
    Explanations

    terms related to political scandals, especially involving Russia and financial crimes

    oai_token-act-pair · gemini-2.0-flash

    cover

    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
     تضيفلها
    -0.71
     \\
    -0.54
     Calf
    -0.54
    .*")]
    -0.52
    Parcelize
    -0.51
    хіво
    -0.51
     useStyles
    -0.51
    íncia
    -0.50
     Öster
    -0.50
    Gemeinden
    -0.50
    POSITIVE LOGITS
     Covered
    0.68
    Cover
    0.68
     cover
    0.66
    cover
    0.66
    COVER
    0.65
     Covering
    0.65
     covered
    0.64
     covering
    0.64
    covered
    0.63
     covers
    0.62
    Activations Density 4.789%

    No Known Activations