© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14063
    Prev
    Next
    INDEX
    Explanations

    words related to emotional evaluation, both positive and negative

    oai_token-act-pair · gemini-2.0-flash

    impressed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     impressed
    -1.27
     surprised
    -1.20
    <bos>
    -1.06
     amazed
    -1.04
     disappointed
    -1.04
     shocked
    -1.02
     astonished
    -1.00
     dismayed
    -0.98
     impress
    -0.96
     surprise
    -0.94
    POSITIVE LOGITS
     resourceCulture
    0.77
    antMatchers
    0.65
    TypedDataSet
    0.64
    expandindo
    0.62
     transfieras
    0.62
    rusted
    0.59
     فريبيس
    0.57
    ServletConfig
    0.57
    __(/*!
    0.57
    netbeans
    0.56
    Activations Density 5.580%

    No Known Activations