© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to machine learning and data analysis

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     purpoſe
    -0.75
    WriteBarrier
    -0.74
    ViewFeatures
    -0.73
    isSuccessful
    -0.65
     Roskov
    -0.62
    basicConfig
    -0.62
    GEBURTS
    -0.61
     pleaſure
    -0.60
     referenties
    -0.60
     raiſ
    -0.60
    POSITIVE LOGITS
     deal
    0.52
     getModel
    0.51
     model
    0.51
     Model
    0.47
    ches
    0.47
    Model
    0.47
    deal
    0.46
    argout
    0.44
     exploit
    0.44
     Section
    0.44
    Activations Density 4.915%

    No Known Activations