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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 6-GEMMASCOPE-TRANSCODER-16K
    4. 14150
    Prev
    Next
    INDEX
    Explanations

    html and LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ↵↵
    -0.48
    <eos>
    -0.47
    <bos>
    -0.46
    <h2>
    -0.43
     pointing
    -0.40
     The
    -0.40
    I
    -0.40
    The
    -0.39
     finais
    -0.38
    Do
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    LookAnd
    0.82
     AssemblyProduct
    0.82
    bootstrapcdn
    0.76
    AutoScaleMode
    0.73
    mybatisplus
    0.72
     gainera
    0.71
     Baillargeon
    0.71
     consultato
    0.71
    )';
    0.69
    Activations Density 1.545%

    No Known Activations