© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12432
    Prev
    Next
    INDEX
    Explanations

    sentences that describe events that are scheduled to happen in the future

    oai_token-act-pair · gemini-2.0-flash

    words related to expectations or forecasts

    np_token-act-pair-logits · gpt-4o-mini

    expected

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyCompany
    -0.72
    WithIOException
    -0.52
     légales
    -0.48
     Bland
    -0.46
    InitVars
    -0.46
    itele
    -0.45
    󠁮
    -0.45
    transQ
    -0.45
    散
    -0.45
     kend
    -0.44
    POSITIVE LOGITS
     expected
    0.99
     Expected
    0.84
    expected
    0.83
     esperamos
    0.80
    SequentialGroup
    0.79
     EXPECT
    0.77
     hoped
    0.76
     Theſe
    0.75
    hopefully
    0.74
    Expected
    0.73
    Activations Density 1.161%

    No Known Activations