© 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. 6892
    Prev
    Next
    INDEX
    Explanations

    words related to aircraft and flight

    oai_token-act-pair · gemini-2.0-flash

    aviation

    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
     yo
    -0.48
     Assignee
    -0.48
    DebuggerNonUser
    -0.48
    ích
    -0.46
     Finch
    -0.46
    AndEndTag
    -0.46
    yo
    -0.46
    voy
    -0.45
    contentLoaded
    -0.45
    illige
    -0.45
    POSITIVE LOGITS
     mergeFrom
    0.60
     doInBackground
    0.59
    tsam
    0.56
    feinander
    0.55
     Commercial
    0.54
    AddAttribute
    0.54
    Coordonnées
    0.54
     Camar
    0.53
    astéro
    0.53
     propOrder
    0.52
    Activations Density 1.968%

    No Known Activations