© 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. 4156
    Prev
    Next
    INDEX
    Explanations

    the word "and" acting as a separator in a list

    oai_token-act-pair · gemini-2.0-flash

    business and technology

    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
    StoryboardSegue
    -0.82
     doInBackground
    -0.79
    apimachinery
    -0.79
    rungsseite
    -0.79
    GraphicsUnit
    -0.79
     Efq
    -0.75
    InvalidProtocol
    -0.75
    AddTagHelper
    -0.72
     désolés
    -0.71
    RenderAtEndOf
    -0.71
    POSITIVE LOGITS
     fin
    0.52
    sa
    0.49
    cas
    0.45
     Cas
    0.43
    ari
    0.42
     alternative
    0.41
    fin
    0.41
     cas
    0.41
     Sa
    0.40
    sin
    0.40
    Activations Density 0.634%

    No Known Activations