© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 676
    Prev
    Next
    INDEX
    Explanations

    mentions of information, especially when combined with language about acquiring, handling, or communicating information.

    oai_token-act-pair · gemini-2.0-flash

    information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Савезне
    -0.73
    MethodManager
    -0.72
    Pautan
    -0.72
     Majefty
    -0.69
     tartalomajánló
    -0.69
    spesies
    -0.69
    хьтан
    -0.64
    findpost
    -0.62
     greateſt
    -0.58
    يكب
    -0.56
    POSITIVE LOGITS
     تضيفلها
    0.46
    enumi
    0.45
    carton
    0.41
    prepareStatement
    0.40
     emp
    0.39
    ст
    0.39
     Pon
    0.39
    ุม
    0.39
    原始内容存档
    0.39
    =<?
    0.39
    Activations Density 8.398%

    No Known Activations