© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 270
    Prev
    Next
    INDEX
    Explanations

    words related to politics, religion, and decision making.

    oai_token-act-pair · gemini-2.0-flash

    opinions, discussions

    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
    <bos>
    -0.85
    าศ
    -0.48
    HasColumnName
    -0.43
     acceptez
    -0.43
     niin
    -0.43
    weile
    -0.42
    WebVitals
    -0.41
    стат
    -0.40
    expandindo
    -0.40
    SuccessListener
    -0.40
    POSITIVE LOGITS
    entibus
    0.68
    ſelf
    0.65
     Majefty
    0.65
    $.
    0.64
    WithEmail
    0.62
    omitempty
    0.62
    cionada
    0.59
     smtplib
    0.59
     Monfieur
    0.59
     itſelf
    0.59
    Activations Density 3.413%

    No Known Activations