© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2338
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to being in busy public places and restaurants

    oai_token-act-pair · gemini-2.0-flash

    Crowded places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagHelperRunner
    -0.96
     CreateTagHelper
    -0.94
     оригіналу
    -0.92
    AndEndTag
    -0.89
    Diweddarwch
    -0.88
     تضيفلها
    -0.86
    Cyfeiriadau
    -0.85
    цездатний
    -0.79
    IntoConstraints
    -0.79
    Tikang
    -0.79
    POSITIVE LOGITS
    tabular
    0.42
    х
    0.41
    h
    0.40
    it
    0.39
    το
    0.39
    Ch
    0.39
    FC
    0.38
    Na
    0.37
    H
    0.37
     душ
    0.37
    Activations Density 1.334%

    No Known Activations