© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3026
    Prev
    Next
    INDEX
    Explanations

    names, especially with titles and combinations of short syllables

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     brancas
    -0.65
     automatiques
    -0.65
     normaux
    -0.63
     vermelhas
    -0.63
     femininas
    -0.61
     mères
    -0.60
     militaires
    -0.58
     rayures
    -0.57
     quelcon
    -0.57
     récentes
    -0.57
    POSITIVE LOGITS
    <bos>
    1.03
     Natale
    0.68
     A
    0.66
     St
    0.66
     As
    0.64
     La
    0.64
     We
    0.63
     Pa
    0.63
     Ad
    0.62
     G
    0.62
    Activations Density 0.953%

    No Known Activations