© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15978
    Prev
    Next
    INDEX
    Explanations

    Objective-C code sections marked with "#pragma mark".

    oai_token-act-pair · gemini-2.0-flash

    mark

    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
    <bos>
    -1.06
    __':
    -0.91
     дописавши
    -0.85
     חיצוניים
    -0.84
     auffi
    -0.84
     kasarigan
    -0.84
     estimés
    -0.83
    脚注の使い方
    -0.80
    __":
    -0.77
    RegressionTest
    -0.77
    POSITIVE LOGITS
     "
    0.65
     
    0.59
     فريبيس
    0.56
     (
    0.54
     God
    0.52
    rolid
    0.52
     vr
    0.50
     many
    0.50
    ITTEN
    0.50
     several
    0.49
    Activations Density 0.712%

    No Known Activations