© 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. 306
    Prev
    Next
    INDEX
    Explanations

    code describing computer architecture, in particular memory and data transfer

    oai_token-act-pair · gemini-2.0-flash

    Underscore

    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
    ImageContext
    -0.75
     is
    -0.72
     form
    -0.71
     feature
    -0.71
     field
    -0.70
     type
    -0.69
     process
    -0.68
     new
    -0.68
     model
    -0.68
     method
    -0.67
    POSITIVE LOGITS
     supérieurs
    1.05
     juridiques
    0.98
     supérieures
    0.97
     mauvaises
    0.95
     colorés
    0.92
     normaux
    0.92
     quelcon
    0.91
     blessés
    0.90
     enfans
    0.90
     refroid
    0.90
    Activations Density 5.603%

    No Known Activations