© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3165
    Prev
    Next
    INDEX
    Explanations

    the word "Super."

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "Super"

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

    Super

    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
     समीक्षाओं
    -0.55
    PropertyGroup
    -0.54
    anyak
    -0.51
    
    -0.50
     DialogInterface
    -0.50
    stoj
    -0.49
    batore
    -0.49
    醐
    -0.49
     MaterialApp
    -0.48
    standalone
    -0.47
    POSITIVE LOGITS
    InjectAttribute
    0.60
     pamamagitan
    0.53
    Попис
    0.51
    IUrlHelper
    0.48
     lccn
    0.47
    管
    0.47
    лади
    0.47
    出版年
    0.46
     xong
    0.45
    FontOfSize
    0.45
    Activations Density 0.315%

    No Known Activations