© 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. 3506
    Prev
    Next
    INDEX
    Explanations

    text containing words related to helping youth and social justice as well as the preposition "for".

    oai_token-act-pair · gemini-2.0-flash

    education

    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
    MessageTagHelper
    -0.59
    GHIJKLM
    -0.52
     Faso
    -0.49
    リート
    -0.49
    ględ
    -0.47
     Am
    -0.44
    shutil
    -0.44
    ாள
    -0.43
    ssan
    -0.43
     la
    -0.42
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.85
    rrggbb
    0.70
     Paglinawan
    0.69
    AddHtmlAttribute
    0.66
     linkovi
    0.64
    
    0.61
    UnknownFieldSet
    0.60
     Duckworth
    0.58
    Filmografia
    0.57
    manos
    0.55
    Activations Density 1.474%

    No Known Activations