© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    verbs that describe actions

    oai_token-act-pair · gemini-2.0-flash

    actions/sensory experiences

    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
     comigo
    -0.68
     genoux
    -0.58
     cérami
    -0.57
     conmigo
    -0.57
     mūsų
    -0.55
     épaules
    -0.54
     rayures
    -0.54
    ="./
    -0.54
     jambes
    -0.53
     hombro
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.58
    󠁿
    0.51
     Réponses
    0.50
     stumps
    0.49
     donuts
    0.48
     checkers
    0.48
     quilts
    0.48
     lemons
    0.47
     grooms
    0.47
     Tabasco
    0.47
    Activations Density 10.627%

    No Known Activations