© 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. 11898
    Prev
    Next
    INDEX
    Explanations

    words related to processes and systems

    oai_token-act-pair · gemini-2.0-flash

    mechanisms related to processes

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

    mechanism

    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
    XmlAccessorType
    -0.84
     propOrder
    -0.81
    +#+
    -0.79
    IUrlHelper
    -0.76
    VIAF
    -0.75
    GeneratedCode
    -0.74
    stdc
    -0.73
     ISNI
    -0.72
    complexContent
    -0.70
    GEBURTSDATUM
    -0.69
    POSITIVE LOGITS
    вості
    0.43
    voy
    0.43
     geführt
    0.42
    avez
    0.41
     TRE
    0.39
    rimos
    0.39
     робити
    0.38
    夠
    0.38
     пропуска
    0.37
    reatment
    0.36
    Activations Density 10.739%

    No Known Activations