© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4390
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the healthcare industry

    oai_token-act-pair · gemini-2.0-flash

    ethics and morals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    BagLayout
    -0.65
    发表于
    -0.61
    HomeAsUpEnabled
    -0.60
    HtmlAttribute
    -0.56
    uminense
    -0.56
     ISNI
    -0.55
    GOTREF
    -0.54
    theros
    -0.54
    enschappen
    -0.53
    bilisi
    -0.53
    POSITIVE LOGITS
    integrity
    0.65
     integrity
    0.63
     professionalism
    0.60
    حياتها
    0.59
     honesty
    0.59
     zéro
    0.58
     consistency
    0.57
    __);
    0.56
    حياته
    0.55
     attention
    0.53
    Activations Density 3.052%

    No Known Activations