© 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. 12082
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to basketball teams and contracts

    oai_token-act-pair · gemini-2.0-flash

    Sports/news articles

    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
     Free
    -0.56
    oredCriteria
    -0.56
    DockStyle
    -0.54
    Free
    -0.53
    ConstraintMaker
    -0.50
    readString
    -0.48
     free
    -0.48
    RTEX
    -0.47
    RectangleBorder
    -0.47
    WebElementEntity
    -0.47
    POSITIVE LOGITS
    Portail
    0.68
     henvisninger
    0.57
    dillera
    0.57
    äsident
    0.52
     thiệu
    0.51
    rungsseite
    0.50
     []:
    0.50
     Formats
    0.50
     Sheeran
    0.50
    illai
    0.49
    Activations Density 2.676%

    No Known Activations