© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12807
    Prev
    Next
    INDEX
    Explanations

    words related to politics and negativity

    oai_token-act-pair · gemini-2.0-flash

    piece

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Wiktionnaire
    -0.49
    reuung
    -0.47
    currentThread
    -0.43
    Aún
    -0.43
    unnitel
    -0.42
     بوده
    -0.41
    uestamente
    -0.41
     продъл
    -0.41
    rentiel
    -0.40
     continuation
    -0.39
    POSITIVE LOGITS
    webElementXpaths
    0.81
    +#+#
    0.77
     beginnetje
    0.75
     оригіналу
    0.69
     gradualmente
    0.67
    λέον
    0.66
    StructEnd
    0.65
     Gradually
    0.64
     gradually
    0.64
     rapidly
    0.63
    Activations Density 21.171%

    No Known Activations