© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6647
    Prev
    Next
    INDEX
    Explanations

    code snippets, potentially in multiple languages, that contain errors

    oai_token-act-pair · gemini-2.0-flash

    初心者

    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
     C
    -0.87
     N
    -0.86
     T
    -0.85
     R
    -0.82
     U
    -0.79
     v
    -0.79
     L
    -0.79
     p
    -0.78
     M
    -0.78
     G
    -0.78
    POSITIVE LOGITS
     myſelf
    2.14
     Monfieur
    2.09
     itſelf
    2.06
     Efq
    2.03
     Jefus
    2.00
     ſeveral
    1.95
     ſtate
    1.91
     houſe
    1.88
     Majefty
    1.88
     Theſe
    1.87
    Activations Density 1.959%

    No Known Activations