© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10403
    Prev
    Next
    INDEX
    Explanations

    time periods

    oai_token-act-pair · gemini-2.0-flash

    Time and measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     NSCoder
    -0.63
    Portail
    -0.51
    EndContext
    -0.51
    ISSE
    -0.50
     Meksiku
    -0.50
    auré
    -0.49
    nolia
    -0.48
    InstanceState
    -0.48
    laire
    -0.47
    toplas
    -0.47
    POSITIVE LOGITS
     hundred
    1.05
     hour
    1.00
     minute
    0.97
     thousand
    0.97
     million
    0.97
     centimeter
    0.95
     century
    0.94
     kilometer
    0.94
    hundred
    0.94
     decade
    0.92
    Activations Density 11.955%

    No Known Activations