© 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. 938
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "green" in the context of politics, environmentalism, or immigration.

    oai_token-act-pair · gemini-2.0-flash

    green

    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
     green
    -3.23
     Green
    -3.09
    Green
    -3.03
    green
    -2.92
     GREEN
    -2.91
    GREEN
    -2.75
     greens
    -2.33
     Greens
    -2.31
     grüne
    -2.22
     grünen
    -2.19
    POSITIVE LOGITS
     الحره
    0.73
     AssemblyTitle
    0.64
    Vanjske
    0.57
    moveToFirst
    0.53
    byshev
    0.49
    lectron
    0.45
    tvguidetime
    0.44
    UniformLocation
    0.44
    onView
    0.43
    ynb
    0.43
    Activations Density 3.737%

    No Known Activations