© 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. 11999
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gemini-2.0-flash

    expressions of gratitude

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

    thank

    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
     for
    -0.84
    for
    -0.73
     für
    -0.47
     FOR
    -0.46
    rony
    -0.42
     forn
    -0.41
     voor
    -0.41
     يتيمه
    -0.41
    плення
    -0.40
    ッズ
    -0.39
    POSITIVE LOGITS
     initComponents
    0.96
    PerformLayout
    0.86
    onAttach
    0.81
     estimés
    0.79
    uxxxx
    0.77
    DockStyle
    0.74
    ValueStyle
    0.74
     HasFactory
    0.73
    AndEndTag
    0.73
    MarshalTo
    0.72
    Activations Density 4.450%

    No Known Activations