© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14995
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-management of health and files with links

    oai_token-act-pair · gemini-2.0-flash

    Say "management"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Manager
    -1.13
     manager
    -1.04
     managed
    -1.00
     Managers
    -0.98
     Managed
    -0.98
     MANAGER
    -0.97
    manager
    -0.96
     MANAG
    -0.94
    Manager
    -0.93
    Managed
    -0.93
    POSITIVE LOGITS
     direction
    0.77
    expandindo
    0.76
     متعلقه
    0.67
     Drapeau
    0.63
    Geplaatst
    0.60
     Direction
    0.59
    Direction
    0.57
    OGND
    0.56
    پیوند
    0.56
    direction
    0.55
    Activations Density 2.133%

    No Known Activations