© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15309
    Prev
    Next
    INDEX
    Explanations

    words and phrases that highlight the importance of data and scientific findings

    oai_token-act-pair · gemini-2.0-flash

    terms related to results and importance

    np_token-act-pair-logits · gpt-4o-mini

    highlights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     fact
    -0.93
     possibility
    -0.85
     notion
    -0.78
    fact
    -0.77
     prospect
    -0.73
     idea
    -0.70
     need
    -0.69
     requirement
    -0.68
     habit
    -0.67
     urge
    -0.65
    POSITIVE LOGITS
     the
    0.77
    GEBURTSDATUM
    0.65
    MessageTagHelper
    0.63
    rungsseite
    0.59
    AutoScaleMode
    0.58
    SourceChecksum
    0.57
    WithIOException
    0.57
     OFDb
    0.57
     محفوظة
    0.57
     its
    0.56
    Activations Density 4.557%

    No Known Activations