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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2760
    Prev
    Next
    INDEX
    Explanations

    instances where someone is expressing hope or optimism about an event

    oai_token-act-pair · gemini-2.0-flash

    hope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Fab
    -0.43
    beutel
    -0.43
    macher
    -0.42
     Pfund
    -0.41
    Dar
    -0.41
    WriteTo
    -0.41
    </blockquote>
    -0.39
     smtplib
    -0.39
    dar
    -0.39
     behar
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.84
     expect
    0.84
    principalTable
    0.81
    URLException
    0.79
    makeConstraints
    0.78
     Roskov
    0.75
    andExpect
    0.75
     expectation
    0.74
     propOrder
    0.74
     hope
    0.74
    Activations Density 0.857%

    No Known Activations