© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13112
    Prev
    Next
    INDEX
    Explanations

    verbs that describes physical actions.

    oai_token-act-pair · gemini-2.0-flash

    Involvement or Participation

    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
     together
    -2.98
    together
    -2.70
     Together
    -2.59
    Together
    -2.50
     TOGETHER
    -2.28
     juntos
    -2.05
     împreună
    -1.72
    gether
    -1.71
     insieme
    -1.63
     вместе
    -1.56
    POSITIVE LOGITS
     with
    0.62
    isolate
    0.41
    ské
    0.39
    nern
    0.39
     nearest
    0.37
     deň
    0.37
     ľ
    0.37
     avec
    0.36
     sisi
    0.36
    andingan
    0.36
    Activations Density 4.307%

    No Known Activations