© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3631
    Prev
    Next
    INDEX
    Explanations

    words related to procedures or instructions, often in the context of retail or online tasks

    oai_token-act-pair · gemini-2.0-flash

    actions, instructions

    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
    NotBe
    -0.58
    RegressionTest
    -0.54
    Have
    -0.50
    íncia
    -0.49
    DebuggerStep
    -0.48
    No
    -0.47
     tenido
    -0.47
    have
    -0.46
    were
    -0.46
     nejsou
    -0.45
    POSITIVE LOGITS
     The
    1.22
     It
    1.02
    The
    0.75
     A
    0.75
     They
    0.72
     Their
    0.69
     Each
    0.66
     All
    0.65
    It
    0.65
     This
    0.65
    Activations Density 18.120%

    No Known Activations