© 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. 1876
    Prev
    Next
    INDEX
    Explanations

    words related to actions or decisions, especially attempts to attain a desired outcome

    oai_token-act-pair · gemini-2.0-flash

    adverbs indicating degree or manner

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

    interactions and responses

    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
    astéroïdes
    -0.82
    pertino
    -0.59
    Vidite
    -0.59
    kega
    -0.57
     déc
    -0.57
    Panamoan
    -0.56
    expandindo
    -0.56
    UNTS
    -0.56
     الحره
    -0.55
    énario
    -0.54
    POSITIVE LOGITS
     meaningfully
    0.66
     qualitatively
    0.57
     substantially
    0.54
     asynchronously
    0.54
     obliquely
    0.52
     favorably
    0.52
     manually
    0.50
     horizontally
    0.50
     considerably
    0.50
     significantly
    0.50
    Activations Density 11.001%

    No Known Activations