© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14366
    Prev
    Next
    INDEX
    Explanations

    mentions of a quantity, a body part, and a descriptive adjective preceding a noun.

    oai_token-act-pair · gemini-2.0-flash

    body, directions, groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bénéfices
    -0.93
    __':
    -0.84
     touristes
    -0.82
     travailleurs
    -0.81
    __':
    -0.81
     preuves
    -0.80
     page
    -0.79
     épaules
    -0.78
     investissements
    -0.78
     vérit
    -0.77
    POSITIVE LOGITS
     rooms
    0.61
     groups
    0.60
    groups
    0.59
     Groups
    0.57
    rooms
    0.56
     fields
    0.56
     frames
    0.56
     domains
    0.56
    Groups
    0.56
    frames
    0.53
    Activations Density 4.879%

    No Known Activations