© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3284
    Prev
    Next
    INDEX
    Explanations

    language commonly used in job postings and car advertisements

    oai_token-act-pair · gemini-2.0-flash

    Product/service quality

    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
    saraba
    -0.63
    ilerini
    -0.47
    ']))
    -0.46
    )}</
    -0.46
    #![
    -0.46
    }))
    -0.45
     iArr
    -0.45
     ammat
    -0.45
    ticoli
    -0.44
    })}\
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.79
    TestingModule
    0.74
    UnsafeEnabled
    0.73
    SpringBootTest
    0.67
     صوتيه
    0.66
    DoubleQuotes
    0.65
    Geplaatst
    0.63
     تانيه
    0.63
    afficheront
    0.62
    BSS
    0.61
    Activations Density 14.374%

    No Known Activations