© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3806
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to comprehension, understanding or planning

    oai_token-act-pair · gemini-2.0-flash

    understand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    álat
    -0.57
     purpoſe
    -0.56
     karş
    -0.56
    enseignements
    -0.52
    ítě
    -0.51
     uncin
    -0.50
    Amar
    -0.49
    obacz
    -0.49
     мәкал
    -0.49
     dė
    -0.48
    POSITIVE LOGITS
     the
    0.77
    WriteTagHelper
    0.70
    __(/*!
    0.63
     ExecuteAsync
    0.63
    ADVERTISEMENT
    0.62
     AspNetCore
    0.60
    EDEFAULT
    0.59
    __))
    0.57
    enschaften
    0.57
     that
    0.56
    Activations Density 10.911%

    No Known Activations