© 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. 14347
    Prev
    Next
    INDEX
    Explanations

    phrases that describe money making, significance, and potential

    oai_token-act-pair · gemini-2.0-flash

    words related to quality or value

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

    adequacy, worth

    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
    Extremely
    -0.63
    Very
    -0.61
    Entire
    -0.59
    BeginContext
    -0.59
     Extremely
    -0.58
     Entire
    -0.56
     Very
    -0.54
    extremely
    -0.51
    very
    -0.48
     Ráp
    -0.47
    POSITIVE LOGITS
     decent
    0.79
     respectable
    0.68
     adequate
    0.68
    DockStyle
    0.66
     respec
    0.64
     worthy
    0.63
     decently
    0.62
     worthwhile
    0.61
     autorytatywna
    0.57
     Decent
    0.56
    Activations Density 1.404%

    No Known Activations