© 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. 5122
    Prev
    Next
    INDEX
    Explanations

    phrases from a Scandinavian language, possibly Danish or Norwegian

    oai_token-act-pair · gemini-2.0-flash

    ny

    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
     pitié
    -0.72
     Pristupljeno
    -0.71
     fotográfica
    -0.71
     vectorielle
    -0.70
     fumée
    -0.68
     immédi
    -0.68
     صوتيه
    -0.68
     manqué
    -0.68
     thermique
    -0.66
     énergétique
    -0.66
    POSITIVE LOGITS
     grand
    0.56
     large
    0.56
     I
    0.55
    initComponents
    0.52
     more
    0.49
    Personensuche
    0.49
     possible
    0.48
    …
    0.47
     […]
    0.47
     transfieras
    0.47
    Activations Density 0.131%

    No Known Activations