© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1143
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or businesses along with related contextual words.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    RegressionTest
    -0.81
     @"/
    -0.68
     betweenstory
    -0.57
     tartalomajánló
    -0.53
    awtextra
    -0.52
    帖最后由
    -0.52
    IsContent
    -0.51
    __*/
    -0.50
     />);
    -0.48
    rache
    -0.47
    POSITIVE LOGITS
     Walkover
    0.64
     video
    0.63
     Video
    0.60
     vidéo
    0.60
    video
    0.59
    раздо
    0.56
    Video
    0.55
     VIDEO
    0.51
    paravant
    0.51
    AutoScaleMode
    0.50
    Activations Density 2.913%

    No Known Activations