© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7650
    Prev
    Next
    INDEX
    Explanations

    text related to Greek mythology, specifically about a person named Dymas

    oai_token-act-pair · gemini-2.0-flash

    classical references

    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
     تانيه
    -0.62
    prefixer
    -0.59
    
    -0.55
    istani
    -0.54
    Abitanti
    -0.52
    ukone
    -0.52
    InvalidProtocol
    -0.52
    aarrggbb
    -0.51
    demies
    -0.49
     NAV
    -0.49
    POSITIVE LOGITS
     Jove
    0.62
     Bacchus
    0.55
     Dionys
    0.54
     Lucius
    0.51
     Eros
    0.50
     Pythagoras
    0.50
    alnız
    0.50
     Muses
    0.49
     Keats
    0.49
     Scip
    0.49
    Activations Density 20.506%

    No Known Activations