© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4984
    Prev
    Next
    INDEX
    Explanations

    proper nouns and place names, especially those related to South Asia

    oai_token-act-pair · gemini-2.0-flash

    News/Political content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    IntoConstraints
    -0.86
    GEBURTSDATUM
    -0.74
     pulmonar
    -0.72
     becauſe
    -0.64
     totul
    -0.63
     negru
    -0.63
     Juifs
    -0.60
     Norvège
    -0.59
     abſ
    -0.59
     eenige
    -0.59
    POSITIVE LOGITS
     por
    0.57
    ………………
    0.57
     Bir
    0.56
    SEGUIR
    0.55
    ± 
    0.55
    esez
    0.54
    FloatField
    0.54
    VIRONMENT
    0.54
    ynen
    0.54
    "</
    0.53
    Activations Density 1.601%

    No Known Activations