© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10412
    Prev
    Next
    INDEX
    Explanations

    text discussing graph theory and trees

    oai_token-act-pair · gemini-2.0-flash

    child

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    DotNetBar
    -0.85
    adaptiveStyles
    -0.79
     مشين
    -0.78
    FormTagHelper
    -0.75
    MemoryWarning
    -0.75
     MessageBoxIcon
    -0.74
    +#+#
    -0.74
    ⓧ
    -0.73
    Hochspringen
    -0.70
    UnsafeEnabled
    -0.68
    POSITIVE LOGITS
    <bos>
    0.90
    ToLeft
    0.45
    tagHelper
    0.43
    (
    0.42
    ↵
    0.42
     kleinere
    0.41
     hellen
    0.41
     quæ
    0.40
    _
    0.40
    <i>
    0.38
    Activations Density 2.171%

    No Known Activations