© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1759
    Prev
    Next
    INDEX
    Explanations

    words related to ending support for software

    oai_token-act-pair · gemini-2.0-flash

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Limit
    -0.46
     gene
    -0.46
    bby
    -0.45
    LayoutInflater
    -0.45
     LIMIT
    -0.44
     limit
    -0.43
     pie
    -0.43
     nave
    -0.43
    蕾
    -0.42
     Lay
    -0.42
    POSITIVE LOGITS
     snippetHide
    0.77
    tvguidetime
    0.75
    GEBURTSDATUM
    0.67
    oredCriteria
    0.61
    AddTagHelper
    0.60
     çöz
    0.59
     Tenga
    0.59
     '{@
    0.59
    ValueStyle
    0.59
    Бахар
    0.59
    Activations Density 0.963%

    No Known Activations