© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13085
    Prev
    Next
    INDEX
    Explanations

    phrases containing "own," "has," and "their" that describe properties belonging to a person or thing.

    oai_token-act-pair · gemini-2.0-flash

    own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RegressionTest
    -0.57
    Trama
    -0.56
     period
    -0.54
     NoSuch
    -0.50
    Publicado
    -0.50
     fast
    -0.49
     vỏ
    -0.49
    ########.
    -0.48
     afore
    -0.48
     Schwartz
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.69
     Chwiliwch
    0.63
     Ressources
    0.63
    ]-->
    0.63
     handleMessage
    0.62
     برانيه
    0.58
    NewUrlParser
    0.55
    Individual
    0.54
    }{||
    0.54
     individuelles
    0.54
    Activations Density 2.435%

    No Known Activations