© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2772
    Prev
    Next
    INDEX
    Explanations

    words related to experiments and study results

    oai_token-act-pair · gemini-2.0-flash

    represent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     represent
    -2.33
     REPRESENT
    -2.14
     representing
    -2.09
    represent
    -2.08
     represents
    -2.06
     represented
    -2.06
     representation
    -2.06
    Represent
    -2.05
     Represent
    -1.98
    representing
    -1.95
    POSITIVE LOGITS
     topi
    0.47
     Loaf
    0.45
    sitive
    0.45
     Quarter
    0.45
    insics
    0.45
     Batch
    0.45
     Pauly
    0.44
     PyTuple
    0.44
    Semi
    0.44
    ętr
    0.43
    Activations Density 12.972%

    No Known Activations