© 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. 15186
    Prev
    Next
    INDEX
    Explanations

    financial terms and related prepositions

    oai_token-act-pair · gemini-2.0-flash

    financial terms related to mortgages

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

    finance/mortgages

    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
     Jefus
    -0.75
     ioutil
    -0.71
     pleaſure
    -0.70
    bootstrapcdn
    -0.69
     purpoſe
    -0.69
    évaluateur
    -0.67
     ſmall
    -0.66
     juſt
    -0.66
     uſe
    -0.65
     uſed
    -0.64
    POSITIVE LOGITS
     sub
    0.62
     Sub
    0.47
    fő
    0.47
    Lynne
    0.45
     F
    0.45
    sub
    0.45
     C
    0.44
     A
    0.43
     f
    0.41
    文書
    0.41
    Activations Density 0.666%

    No Known Activations