© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8252
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code and configuration snippets

    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
     kaarangay
    -0.95
     &___
    -0.88
    ftagPool
    -0.80
     transfieras
    -0.80
     CanadaChoose
    -0.77
    RectangleBorder
    -0.75
     pinulongan
    -0.75
    +#+
    -0.73
     Spisak
    -0.73
    AndEndTag
    -0.71
    POSITIVE LOGITS
    ↵↵
    0.78
    ↵
    0.58
    <bos>
    0.51
    What
    0.50
    The
    0.49
     The
    0.49
     What
    0.47
     I
    0.46
    </blockquote>
    0.46
     przys
    0.44
    Activations Density 1.035%

    No Known Activations