© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10690
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to nature and tourism, especially hiking and water.

    oai_token-act-pair · gemini-2.0-flash

    outdoor activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    atguigu
    -0.59
    linearGradient
    -0.47
    UIControlState
    -0.44
     Ajoutez
    -0.44
    ็จ
    -0.43
    letter
    -0.43
     acelerar
    -0.41
    gnore
    -0.41
     phím
    -0.41
     Pittman
    -0.40
    POSITIVE LOGITS
    RectangleBorder
    0.74
     betweenstory
    0.69
    AnchorTagHelper
    0.65
    PMailer
    0.63
     pinulongan
    0.63
     kasarigan
    0.62
    XmlAccessType
    0.61
    jsonwebtoken
    0.61
     CreateTagHelper
    0.60
    таратура
    0.55
    Activations Density 1.142%

    No Known Activations