© 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. 4429
    Prev
    Next
    INDEX
    Explanations

    a variety of verbs with moderate activation when surrounded by other words.

    oai_token-act-pair · gemini-2.0-flash

    Reactions

    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
     delight
    -0.68
     surprise
    -0.65
    surprise
    -0.60
     pleasure
    -0.60
     disappointment
    -0.58
    delight
    -0.57
     joy
    -0.56
     shame
    -0.55
     horror
    -0.54
     relief
    -0.52
    POSITIVE LOGITS
    rungsseite
    0.94
     Normdatei
    0.71
    featureID
    0.69
    (;;)
    0.68
    iastical
    0.68
     EconPapers
    0.68
    InjectAttribute
    0.67
    uxxxx
    0.66
    __':
    0.65
    mybatisplus
    0.64
    Activations Density 2.516%

    No Known Activations