© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8535
    Prev
    Next
    INDEX
    Explanations

    words related to intent and planning for the future.

    oai_token-act-pair · gemini-2.0-flash

    Legal/Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ('/:
    -0.59
     Sensi
    -0.53
    chaik
    -0.52
    (;;)
    -0.52
    engar
    -0.52
    ynos
    -0.51
    izamos
    -0.51
    esgue
    -0.50
    ("/:
    -0.50
    obod
    -0.50
    POSITIVE LOGITS
    <bos>
    1.02
     intention
    0.94
     planned
    0.93
     intentions
    0.92
     intends
    0.91
     plans
    0.88
     intend
    0.88
     Intention
    0.85
    intention
    0.83
     intending
    0.83
    Activations Density 0.753%

    No Known Activations