© 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. 5867
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms, and codes

    oai_token-act-pair · gemini-2.0-flash

    cancer studies

    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
     onAnimation
    -0.60
    Köln
    -0.57
    Schöne
    -0.54
    Leipzig
    -0.54
    München
    -0.53
    Salz
    -0.52
    Große
    -0.52
     SqlCommand
    -0.52
    Meine
    -0.52
    Sådan
    -0.52
    POSITIVE LOGITS
     générations
    0.64
     cœurs
    0.54
     gouvernements
    0.54
     zufolge
    0.54
     quantités
    0.52
     communs
    0.52
     communautés
    0.49
     pouvoirs
    0.49
     vœux
    0.49
     chaînes
    0.48
    Activations Density 15.275%

    No Known Activations