© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6491
    Prev
    Next
    INDEX
    Explanations

    instances of time and situations occurring over periods of time

    oai_token-act-pair · gemini-2.0-flash

    variants of "is" and "are"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    awtextra
    -0.77
    tagext
    -0.74
    بوابة
    -0.73
     CURIAM
    -0.70
    OGND
    -0.70
    
    -0.68
    Portail
    -0.68
     ModelExpression
    -0.67
    twimg
    -0.67
     Ready
    -0.67
    POSITIVE LOGITS
     is
    1.16
     are
    0.82
     está
    0.69
    are
    0.65
     están
    0.63
     êtes
    0.62
     sommes
    0.62
    的是
    0.61
     estoy
    0.57
     Is
    0.57
    Activations Density 0.975%

    No Known Activations