© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10102
    Prev
    Next
    INDEX
    Explanations

    grammatical articles and propositions

    oai_token-act-pair · gemini-2.0-flash

    variations of "good"

    np_token-act-pair-logits · gpt-4o-mini

    good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    
    -0.60
    webElementGuid
    -0.56
    QMetaType
    -0.55
    COUVER
    -0.55
     EconPapers
    -0.53
    Geplaatst
    -0.51
    WriteAttribute
    -0.49
     مرئيه
    -0.49
    TagMode
    -0.47
    ksesta
    -0.46
    POSITIVE LOGITS
     good
    3.19
    good
    2.89
    Good
    2.61
     GOOD
    2.45
     Good
    2.45
    GOOD
    2.38
     buena
    1.86
     buenas
    1.82
     gute
    1.78
     bonne
    1.74
    Activations Density 2.691%

    No Known Activations