© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6583
    Prev
    Next
    INDEX
    Explanations

    words related to the service and legal industries, including courts, bars, markets, dishes and restaurants

    oai_token-act-pair · gemini-2.0-flash

    course topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ‘
    -0.56
    #+#
    -0.55
     pstmt
    -0.51
     suo
    -0.50
    \_
    -0.50
    existsSync
    -0.49
     T
    -0.48
    Pyx
    -0.48
     redor
    -0.47
    glBindTexture
    -0.47
    POSITIVE LOGITS
     purpoſe
    0.89
     reaſon
    0.86
     pleaſure
    0.85
     ſever
    0.81
     houſe
    0.79
     Diſ
    0.79
    ſelves
    0.79
     Majefty
    0.79
     Eſ
    0.78
     Reſ
    0.78
    Activations Density 20.924%

    No Known Activations