© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12508
    Prev
    Next
    INDEX
    Explanations

    verbs related to changing conditions or legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    Change/varying conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     fevere
    -0.74
     purpoſe
    -0.73
     Jefus
    -0.69
     ſche
    -0.66
     whoſe
    -0.65
     Monfieur
    -0.65
     myſelf
    -0.65
    ſelf
    -0.64
     ſta
    -0.64
     chofe
    -0.63
    POSITIVE LOGITS
    featureID
    0.67
    abestanden
    0.54
     disparu
    0.53
     trajets
    0.52
     come
    0.52
     be
    0.51
     gynhyrchwyd
    0.51
    -------------</
    0.50
    junct
    0.50
     become
    0.50
    Activations Density 5.282%

    No Known Activations