© 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. 13530
    Prev
    Next
    INDEX
    Explanations

    colons and backslashes

    oai_token-act-pair · gemini-2.0-flash

    special characters and unconventional formats

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

    :

    np_max-act-logits · gemini-2.0-flash
    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
    SceneManagement
    -0.53
    BackStack
    -0.51
    Descripció
    -0.46
    kmäler
    -0.46
    WebpackPlugin
    -0.45
    tumblr
    -0.45
    ImageField
    -0.45
     Laplace
    -0.45
    endphp
    -0.45
     tiguan
    -0.45
    POSITIVE LOGITS
    oredCriteria
    0.65
    ///</
    0.65
     Савезне
    0.60
    datable
    0.58
     Мексичка
    0.58
    tagHelperRunner
    0.57
    AutoScaleMode
    0.55
    pach
    0.54
    complexContent
    0.50
    fjspx
    0.50
    Activations Density 0.105%

    No Known Activations