© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6387
    Prev
    Next
    INDEX
    Explanations

    text related to vehicle diagnostics and standards

    oai_token-act-pair · gemini-2.0-flash

    vehicle-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    vehicles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    migrationBuilder
    -0.84
    VersionUID
    -0.70
    writeField
    -0.70
    !*\
    -0.68
    yntaxException
    -0.67
    SerializedSize
    -0.63
     protoimpl
    -0.62
    hObject
    -0.60
    saraba
    -0.60
    Abitanti
    -0.60
    POSITIVE LOGITS
     vehicle
    0.55
     drives
    0.52
     drive
    0.52
     Vehicle
    0.51
     vehic
    0.51
     kendaraan
    0.49
     vehicles
    0.49
    しくは
    0.48
     Vehicles
    0.48
    Vehicle
    0.47
    Activations Density 1.278%

    No Known Activations