© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    scientific and technical writing

    oai_token-act-pair · gemini-2.0-flash

    causal conjunctions

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

    then

    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
     engraçadas
    -0.58
    expandindo
    -0.50
     henvisninger
    -0.47
    __(/*!
    -0.45
     consommateurs
    -0.41
     morire
    -0.40
     endregion
    -0.40
    onel
    -0.40
     jouets
    -0.39
     générales
    -0.39
    POSITIVE LOGITS
     then
    3.42
    then
    2.63
     então
    2.55
     entonces
    2.42
     therefore
    2.39
     thus
    2.39
     Then
    2.31
    Then
    2.27
     alors
    2.20
     THEN
    2.17
    Activations Density 6.256%

    No Known Activations