© 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. 16100
    Prev
    Next
    INDEX
    Explanations

    words related to hockey, school and sports teams

    oai_token-act-pair · gemini-2.0-flash

    school years

    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
     senior
    -1.54
    Senior
    -1.45
     Senior
    -1.44
    senior
    -1.42
     seniors
    -1.27
     junior
    -1.26
     SENIOR
    -1.20
    SENIOR
    -1.12
     juniors
    -1.09
    junior
    -1.09
    POSITIVE LOGITS
    istoitu
    0.56
     Biôgrafia
    0.54
     textStatus
    0.54
    ycznego
    0.53
     spécialisé
    0.53
    racia
    0.52
    ftant
    0.51
    ChildScrollView
    0.51
    près
    0.50
    slideUp
    0.50
    Activations Density 2.590%

    No Known Activations