© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14129
    Prev
    Next
    INDEX
    Explanations

    the word "and".

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or code snippets

    np_token-act-pair-logits · gpt-4o-mini

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ipedi
    -0.48
    ticons
    -0.45
     Zem
    -0.44
    <bos>
    -0.43
    th
    -0.42
     protoimpl
    -0.42
     St
    -0.40
    ifiable
    -0.40
     Gran
    -0.40
     He
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.75
    رشف
    0.62
     kasarigan
    0.62
     initWithFrame
    0.62
     AssemblyCulture
    0.61
    tvguidetime
    0.61
     AssemblyCompany
    0.60
    \{\\
    0.59
    مصادر
    0.59
    ")));
    0.58
    Activations Density 1.622%

    No Known Activations