© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    verbs related to scientific research, analysis, and methodology

    oai_token-act-pair · gemini-2.0-flash

    inclusion of specifics or details

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

    Describing contents or components

    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
     gustaba
    -0.43
    šn
    -0.43
     kanyang
    -0.42
     sẻ
    -0.42
     provato
    -0.42
     že
    -0.41
    áját
    -0.41
     én
    -0.40
     rencontré
    -0.40
    jét
    -0.40
    POSITIVE LOGITS
     ſeveral
    0.86
     propOrder
    0.83
    脚注の使い方
    0.81
     both
    0.81
     createState
    0.80
     a
    0.77
     myſelf
    0.76
    iffion
    0.75
     several
    0.73
     Efq
    0.73
    Activations Density 7.495%

    No Known Activations