© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4497
    Prev
    Next
    INDEX
    Explanations

    words in different languages related to data and iterations, especially in the context of Facebook

    oai_token-act-pair · gemini-2.0-flash

    Foreign language text

    np_max-act · gemini-2.0-flash
    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
    abestanden
    -0.73
    "",
    -0.65
     ""
    -0.64
     Theſe
    -0.64
    usermodel
    -0.61
     "");
    -0.61
    !")
    -0.60
    NOPQRST
    -0.58
    SuppressLint
    -0.58
     Reſ
    -0.58
    POSITIVE LOGITS
    <bos>
    0.87
    //
    0.85
    /*
    0.81
    TAWA
    0.67
     MonoBehaviour
    0.63
     encomp
    0.61
    yntaxException
    0.60
    ımda
    0.59
    endpush
    0.58
     ghiaccio
    0.58
    Activations Density 1.788%

    No Known Activations