© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3566
    Prev
    Next
    INDEX
    Explanations

    Spanish names or words

    oai_token-act-pair · gemini-2.0-flash

    specific names or terms in Spanish context

    np_token-act-pair-logits · gpt-4o-mini

    foreign languages

    np_max-act-logits · gemini-2.0-flash

    el/del

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyCulture
    -0.77
    nitus
    -0.73
    LookAnd
    -0.70
    
    -0.69
     NgModule
    -0.65
     doGet
    -0.61
    Obrázky
    -0.61
    OGND
    -0.59
    EndInit
    -0.58
    AndEndTag
    -0.57
    POSITIVE LOGITS
    олові
    0.52
     nữa
    0.49
     barium
    0.42
     parall
    0.42
     Suom
    0.41
    Ref
    0.41
     quedado
    0.41
    пуль
    0.41
     quite
    0.41
    ուն
    0.41
    Activations Density 0.640%

    No Known Activations