© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4067
    Prev
    Next
    INDEX
    Explanations

    expressions of support, gratitude, and agreement within online comments/dialogues.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    aarrggbb
    -0.46
    MUM
    -0.42
     gynhyrchwyd
    -0.42
     امريكا
    -0.42
     guys
    -0.42
    プリング
    -0.41
    anella
    -0.40
     Associated
    -0.40
     Hä
    -0.40
    لمانيا
    -0.39
    POSITIVE LOGITS
    GREAT
    0.82
    complexContent
    0.80
    Great
    0.77
     Great
    0.75
    ValueGeneration
    0.71
     GREAT
    0.69
    writeField
    0.68
    great
    0.67
    DockStyle
    0.65
     great
    0.64
    Activations Density 8.848%

    No Known Activations