© 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. 5010
    Prev
    Next
    INDEX
    Explanations

    references to the past and the concept of "left"

    oai_token-act-pair · gemini-2.0-flash

    "left" or "last"

    np_max-act · gemini-2.0-flash

    left or last

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    RegressionTest
    -0.83
    rawDesc
    -0.76
    PhysRevD
    -0.70
    "?>
    -0.70
    клопе
    -0.70
    ={({
    -0.66
     autorytatywna
    -0.66
    ）』
    -0.66
    MENAFN
    -0.65
    IGraphics
    -0.65
    POSITIVE LOGITS
    <bos>
    0.59
    I
    0.58
     tartalomajánló
    0.51
     brinquedos
    0.50
    rungsseite
    0.47
     sabbia
    0.47
     hébergement
    0.46
     armas
    0.45
    P
    0.45
    beutel
    0.44
    Activations Density 0.677%

    No Known Activations