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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10497
    Prev
    Next
    INDEX
    Explanations

    phrases related to health, medicine, healthcare policy, scientific articles, and legal texts

    oai_token-act-pair · gemini-2.0-flash

    legal, technical documents

    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
     Rasulullah
    -0.53
     atque
    -0.52
     bluzka
    -0.51
     Aene
    -0.51
     habet
    -0.51
     nostru
    -0.50
    Hulk
    -0.50
     tantum
    -0.50
    meleon
    -0.50
     quidem
    -0.49
    POSITIVE LOGITS
    
    0.70
    Termination
    0.66
    Eligibility
    0.65
    tagHelperRunner
    0.63
    Unemployment
    0.63
    thenReturn
    0.62
     سكانية
    0.61
    Mandatory
    0.61
    Sufficient
    0.61
     Expenditures
    0.61
    Activations Density 43.240%

    No Known Activations