© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15617
    Prev
    Next
    INDEX
    Explanations

    legal language and arguments.

    oai_token-act-pair · gemini-2.0-flash

    legal arguments

    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
    OGND
    -1.05
    enumi
    -0.87
    TagMode
    -0.83
    IntoConstraints
    -0.75
    EndGlobalSection
    -0.73
    ChildScrollView
    -0.72
    <bos>
    -0.71
    makeConstraints
    -0.71
    basicConfig
    -0.71
    脚注の使い方
    -0.70
    POSITIVE LOGITS
     hilo
    0.46
     also
    0.45
    <h5>
    0.43
    зможно
    0.42
    だけ
    0.42
    Pyx
    0.41
     Kanton
    0.41
    mtd
    0.41
    als
    0.40
     правда
    0.40
    Activations Density 9.284%

    No Known Activations