© 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. 234
    Prev
    Next
    INDEX
    Explanations

    scientific language related to naming fossil species, bacteria, and paleontology.

    oai_token-act-pair · gemini-2.0-flash

    Scientific species names

    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
     pleaſure
    -0.50
     þat
    -0.50
     engraçadas
    -0.49
     myſelf
    -0.49
     themſelves
    -0.48
     retrô
    -0.48
     vermelhas
    -0.47
     tatuagens
    -0.45
     fotografico
    -0.45
     Abonnez
    -0.44
    POSITIVE LOGITS
    omyces
    0.79
     تضيفلها
    0.73
     beginnetje
    0.70
    ichthys
    0.69
    opsida
    0.66
    chyma
    0.66
    oplasma
    0.66
    siella
    0.65
    idopsis
    0.65
    chium
    0.65
    Activations Density 18.497%

    No Known Activations