© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12199
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures

    oai_token-act-pair · gemini-2.0-flash

    political figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
      
    -0.51
     re
    -0.42
    sizeCache
    -0.42
    су
    -0.41
     rein
    -0.40
    od
    -0.40
    docx
    -0.40
    :✨
    -0.40
     di
    -0.40
    <bos>
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.84
    OGND
    0.76
    पया
    0.74
     AssemblyVersion
    0.73
     Majefty
    0.72
    AndEndTag
    0.71
    ^(@)
    0.70
     Signalez
    0.70
     becauſe
    0.68
    CodedInputStream
    0.68
    Activations Density 0.259%

    No Known Activations