© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3616
    Prev
    Next
    INDEX
    Explanations

    phrases about something being on one side of something else

    oai_token-act-pair · gemini-2.0-flash

    say side

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     sides
    -1.75
     Sides
    -1.53
    sides
    -1.41
    Sides
    -1.35
     lados
    -0.95
     Seiten
    -0.94
     edges
    -0.94
     walls
    -0.93
     sided
    -0.91
     Edges
    -0.90
    POSITIVE LOGITS
    numerusform
    0.74
     doInBackground
    0.69
    rrggbb
    0.62
    MessageOf
    0.61
     onPostExecute
    0.60
    IsMutable
    0.60
    SharedDtor
    0.60
    InputTagHelper
    0.59
    bootstrapcdn
    0.57
     continúas
    0.56
    Activations Density 3.645%

    No Known Activations