© 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. 381
    Prev
    Next
    INDEX
    Explanations

    words indicating size, degree, length, age, and difference within scientific and health-related contexts

    oai_token-act-pair · gemini-2.0-flash

    measurements

    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
    color
    -1.04
     Color
    -1.02
     Price
    -1.01
    Color
    -1.00
     color
    -1.00
    Price
    -0.98
     colour
    -0.97
    colour
    -0.97
     Value
    -0.95
    value
    -0.93
    POSITIVE LOGITS
    IBarButtonItem
    0.59
    basicConfig
    0.56
     AssemblyTitle
    0.53
     trenches
    0.51
     gawas
    0.51
     OnInit
    0.50
    IonicModule
    0.49
     Bajos
    0.47
     Tapatalk
    0.47
     חיצוניים
    0.47
    Activations Density 4.348%

    No Known Activations