© 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. 10146
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or scientific text

    oai_token-act-pair · gemini-2.0-flash

    words with prime significance or importance

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

    ?

    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
     ſche
    -0.66
     Diſ
    -0.66
     difp
    -0.64
    .[/
    -0.63
     cauſe
    -0.63
     ſtand
    -0.62
     uſe
    -0.62
     Houſe
    -0.61
     inſ
    -0.60
    
    -0.60
    POSITIVE LOGITS
     A
    0.84
     
    0.72
    LabelTagHelper
    0.66
    évaluateur
    0.66
     O
    0.63
     а
    0.58
     المعيارى
    0.58
     o
    0.57
    mpotent
    0.57
    addCriterion
    0.56
    Activations Density 5.102%

    No Known Activations