© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5366
    Prev
    Next
    INDEX
    Explanations

    mentions of US political parties and candidates

    oai_token-act-pair · gemini-2.0-flash

    presidential elections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Bronnen
    -0.75
    Manbalar
    -0.52
     חיצוניים
    -0.52
     gainera
    -0.48
    BackStack
    -0.46
     OMITTED
    -0.46
     AssemblyCulture
    -0.46
    ngrx
    -0.45
    OGND
    -0.45
     Allein
    -0.45
    POSITIVE LOGITS
     presidential
    0.63
     présidenti
    0.61
     entrants
    0.58
     présidentielle
    0.58
     primaire
    0.58
     aspirants
    0.57
     presidencial
    0.57
    FieldBuilder
    0.56
    rok
    0.56
     Presidential
    0.55
    Activations Density 0.959%

    No Known Activations