© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13343
    Prev
    Next
    INDEX
    Explanations

    an overly-verbose, rambling inspirational/self-help message.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RepeatedField
    -0.64
    tonode
    -0.61
    اقرأ
    -0.54
     createState
    -0.52
    writeField
    -0.52
     gbc
    -0.51
     rentrée
    -0.51
    ExtendWith
    -0.50
     Púb
    -0.49
     cappuccio
    -0.49
    POSITIVE LOGITS
    EndGlobalSection
    0.60
     Mardi
    0.49
     EClass
    0.49
     Islanders
    0.49
     sire
    0.49
     pregn
    0.49
     onCreateView
    0.48
    GEBURTSDATUM
    0.47
     afe
    0.46
     anthropology
    0.46
    Activations Density 12.295%

    No Known Activations