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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14431
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly those appearing in scientific and technical writing

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    WriteBarrier
    -0.49
    כא
    -0.48
     informé
    -0.47
    offsetof
    -0.47
    rikan
    -0.47
    lím
    -0.47
    ********
    -0.46
    isset
    -0.46
    dataclass
    -0.45
     Zeitpunkt
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.73
     Савезне
    0.66
    
    0.57
    skraft
    0.56
    ergies
    0.56
    Rhestr
    0.55
    Obfuscated
    0.54
     للاسماء
    0.54
     viol
    0.54
     Signalez
    0.54
    Activations Density 0.596%

    No Known Activations