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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11770
    Prev
    Next
    INDEX
    Explanations

    the letter "G" followed by other letters, and references

    oai_token-act-pair · gemini-2.0-flash

    scientific citations

    np_max-act-logits · 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
     createState
    -0.53
    offsetof
    -0.49
    ToRead
    -0.48
    PyExc
    -0.48
    erweise
    -0.48
    fortawesome
    -0.47
    cipar
    -0.47
     aand
    -0.45
     Wallflower
    -0.44
     BNE
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.63
    SOUNDBITE
    0.62
    
    0.62
    jede
    0.60
    acek
    0.57
    parker
    0.57
    рест
    0.57
    +#+#
    0.56
    lamino
    0.56
    cione
    0.55
    Activations Density 4.563%

    No Known Activations