© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2041
    Prev
    Next
    INDEX
    Explanations

    references to someone's personal pronouns or possessive case

    oai_token-act-pair · gemini-2.0-flash

    words associated with political actions or statements

    np_token-act-pair-logits · gpt-4o-mini

    Politics/News

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     supérieures
    -0.50
     rayures
    -0.48
     autoridades
    -0.45
    ējās
    -0.43
    leyeb
    -0.43
     llaves
    -0.43
     démocratie
    -0.42
     veille
    -0.40
    user
    -0.39
     cotone
    -0.39
    POSITIVE LOGITS
    addContainerGap
    0.82
     comparison
    0.79
     prediction
    0.76
    Билгалдахарш
    0.75
     apology
    0.75
     stance
    0.75
     intention
    0.74
    IntoConstraints
    0.73
    DotNetBar
    0.73
     obligation
    0.73
    Activations Density 2.115%

    No Known Activations