© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11470
    Prev
    Next
    INDEX
    Explanations

    text related to automotive diagnostics and standards

    oai_token-act-pair · gemini-2.0-flash

    automotive diagnostics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Cursors
    -0.50
     Commencez
    -0.45
     sintió
    -0.45
     propOrder
    -0.42
    itaire
    -0.41
     púb
    -0.41
    pleaños
    -0.41
    vosti
    -0.41
    amaha
    -0.40
     sommes
    -0.38
    POSITIVE LOGITS
    +#+#
    0.97
     kaarangay
    0.67
    matchCondition
    0.65
    ngOnInit
    0.64
    WebServlet
    0.60
    といけない
    0.60
     stanovnika
    0.59
     通販
    0.58
    Климат
    0.57
     onOptions
    0.56
    Activations Density 2.196%

    No Known Activations