© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12576
    Prev
    Next
    INDEX
    Explanations

    uses of the first and second person

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ReusableCell
    -0.78
     étoit
    -0.72
     quæ
    -0.69
     pleaſure
    -0.65
     pattes
    -0.65
     يتيمه
    -0.63
    RenderAtEndOf
    -0.62
    RunWith
    -0.61
     sauvages
    -0.61
     håll
    -0.59
    POSITIVE LOGITS
     ostavi
    0.54
    scryfall
    0.51
     AspNetCore
    0.50
    obs
    0.48
     propOrder
    0.48
    reda
    0.47
    EndContext
    0.46
    buss
    0.45
    OBS
    0.45
    Населення
    0.44
    Activations Density 2.243%

    No Known Activations