© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5535
    Prev
    Next
    INDEX
    Explanations

    mentions of both parents being considered together

    oai_token-act-pair · gemini-2.0-flash

    say "parents"

    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
    WithIdentifier
    -0.59
    enumii
    -0.53
    TagHelper
    -0.52
    ništ
    -0.51
     teachers
    -0.50
    OnInit
    -0.50
    woll
    -0.50
     authors
    -0.50
     officers
    -0.49
     waiters
    -0.49
    POSITIVE LOGITS
    ########.
    0.73
    ORAGE
    0.66
     vård
    0.64
     parem
    0.61
     bậc
    0.58
     pă
    0.55
     zákon
    0.54
     guardi
    0.52
    eraard
    0.52
    webElementXpaths
    0.50
    Activations Density 1.809%

    No Known Activations