© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13615
    Prev
    Next
    INDEX
    Explanations

    full names of specific car models and brands (often German)

    oai_token-act-pair · gemini-2.0-flash

    vehicle names and technical terms

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

    Cars and Formula 1

    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
    ContentAsync
    -0.52
     Roskov
    -0.49
    MigrationBuilder
    -0.48
     laboratorio
    -0.47
    watermark
    -0.47
    BeginInit
    -0.46
     kuin
    -0.46
     udaler
    -0.46
    TextHelper
    -0.45
     ISNI
    -0.45
    POSITIVE LOGITS
     MainAxisSize
    0.61
    ModelForm
    0.56
    providedIn
    0.54
     Diri
    0.53
     surla
    0.52
     peix
    0.50
    न्छ
    0.50
     car
    0.49
    esus
    0.49
    pun
    0.49
    Activations Density 0.760%

    No Known Activations