© 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. 391
    Prev
    Next
    INDEX
    Explanations

    mentions of schools or the education system.

    oai_token-act-pair · gemini-2.0-flash

    school

    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
     Eſ
    -0.77
     myſelf
    -0.72
     reaſon
    -0.72
     pleaſure
    -0.71
     ſtate
    -0.71
     Jefus
    -0.71
    ChildScrollView
    -0.70
     Efq
    -0.70
     preſent
    -0.70
     purpoſe
    -0.70
    POSITIVE LOGITS
     mence
    0.47
     áng
    0.45
     me
    0.45
    وده
    0.42
     acontecimientos
    0.41
    chere
    0.40
    verge
    0.40
     Gel
    0.39
     ch
    0.39
     conducta
    0.39
    Activations Density 1.726%

    No Known Activations