© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4029
    Prev
    Next
    INDEX
    Explanations

    LaTeX blocks

    oai_token-act-pair · gemini-2.0-flash

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     tombé
    -0.48
    这句话
    -0.44
     bowing
    -0.43
     pessoais
    -0.42
     idéia
    -0.42
     inapplicable
    -0.41
    ])));
    -0.41
     informe
    -0.41
    <eos>
    -0.40
    מה
    -0.40
    POSITIVE LOGITS
    enumi
    0.82
    脚注の使い方
    0.82
    Хьажоргаш
    0.75
    verwijspagina
    0.71
    المناصب
    0.69
     Chwiliwch
    0.69
    OGND
    0.69
    setupUi
    0.68
     constexpr
    0.67
    期刊论文
    0.66
    Activations Density 1.465%

    No Known Activations