© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5019
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or affinity

    oai_token-act-pair · gemini-2.0-flash

    expressions of affection or love

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

    love

    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
     nakalista
    -0.56
     vœux
    -0.47
     kredit
    -0.46
    Rhestr
    -0.45
     précédentes
    -0.44
     emplois
    -0.44
     travaillons
    -0.43
     donné
    -0.41
     guerres
    -0.41
     anlam
    -0.41
    POSITIVE LOGITS
    sizeCache
    0.88
    帖最后由
    0.79
    BeginInit
    0.77
     Roskov
    0.75
    \{\\
    0.72
     catching
    0.71
    setVerticalGroup
    0.71
    <bos>
    0.69
     autorytatywna
    0.68
    stateProvider
    0.68
    Activations Density 2.296%

    No Known Activations