© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 418
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers, potentially representing memory addresses or codes, especially within code snippets and research papers.

    oai_token-act-pair · gemini-2.0-flash

    say "followed by 0"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <>();
    -0.52
    ());
    -0.52
    IsContent
    -0.50
    ];
    -0.47
     שוליים
    -0.46
    ++
    -0.45
    ]:
    -0.43
    estine
    -0.43
    >();
    -0.43
     للاسماء
    -0.42
    POSITIVE LOGITS
     صوتيه
    0.66
     EconPapers
    0.66
    ❋
    0.58
     grosso
    0.56
    UnknownFieldSet
    0.56
    Šaltiniai
    0.54
    sessions
    0.54
     Alligator
    0.54
     Octubre
    0.53
    IInterface
    0.53
    Activations Density 4.802%

    No Known Activations