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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12162
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions

    oai_token-act-pair · gemini-2.0-flash

    code URLs/database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Ver
    -0.49
     ver
    -0.47
    block
    -0.46
    8
    -0.45
    th
    -0.45
    <eos>
    -0.45
    struct
    -0.45
    red
    -0.44
    ner
    -0.44
    ë
    -0.44
    POSITIVE LOGITS
     purpoſe
    0.98
     Majefty
    0.97
     ſmall
    0.94
     fubject
    0.94
     itſelf
    0.94
     myſelf
    0.92
    Datuak
    0.92
     occaf
    0.91
    ^(@)
    0.90
     ſtate
    0.89
    Activations Density 1.011%

    No Known Activations