© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11476
    Prev
    Next
    INDEX
    Explanations

    a variety of terms including those related to nationality, food, programming/debugging, image representation, and statistics or categorization.

    oai_token-act-pair · gemini-2.0-flash

    scraped data and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     
    -0.58
    ),
    -0.47
    例文帳に追加
    -0.46
     eksempel
    -0.46
    oles
    -0.45
     luchar
    -0.44
    )(
    -0.44
    </strong>
    -0.43
    ,”
    -0.43
    ).
    -0.42
    POSITIVE LOGITS
     Roskov
    1.05
    Personendaten
    0.94
    contentLoaded
    0.94
    parsedMessage
    0.93
     esternos
    0.88
     كومونز
    0.85
     незавершена
    0.84
    oredCriteria
    0.84
    Viitteet
    0.81
     OFDb
    0.80
    Activations Density 3.577%

    No Known Activations