© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1285
    Prev
    Next
    INDEX
    Explanations

    medical or scientific terminology related to human anatomy and processes and/or prepositional phrases involving directional movement or application

    oai_token-act-pair · gemini-2.0-flash

    technical/medical language

    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
     lungs
    -0.64
     ears
    -0.58
     kidneys
    -0.56
     brain
    -0.55
     lips
    -0.54
     eyes
    -0.53
    nees
    -0.53
     pancreas
    -0.52
     cortex
    -0.52
     stomach
    -0.52
    POSITIVE LOGITS
     the
    0.88
     mergeFrom
    0.69
     unknownFields
    0.66
    modelBuilder
    0.65
     linkovi
    0.63
    protoc
    0.62
     defaultstate
    0.58
    PropertyChanging
    0.57
    CopyWith
    0.57
    RTDA
    0.56
    Activations Density 1.008%

    No Known Activations