© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7397
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of gratitude or agreement

    oai_token-act-pair · gemini-2.0-flash

    Academic acknowledgements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Référence
    -0.84
     Roskov
    -0.77
    featureID
    -0.71
    ContentAsync
    -0.68
    AddTagHelper
    -0.66
    RTEX
    -0.63
    ValueStyle
    -0.63
    참고
    -0.63
    IonicModule
    -0.58
    autoconfigure
    -0.58
    POSITIVE LOGITS
    ächlich
    0.50
    ndel
    0.48
     intro
    0.45
     del
    0.44
    NamedQueries
    0.43
    ronesia
    0.42
     introduction
    0.42
    roduction
    0.41
    gatsby
    0.41
    ய
    0.41
    Activations Density 0.867%

    No Known Activations