© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15073
    Prev
    Next
    INDEX
    Explanations

    author and editor information in citations and bylines

    oai_token-act-pair · gemini-2.0-flash

    Publications/Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GHIJKLM
    -0.74
     '{@
    -0.66
    bootstrapcdn
    -0.65
     uiteindelijk
    -0.65
    клопе
    -0.62
    RegressionTest
    -0.60
    achal
    -0.60
     fermés
    -0.59
    versiti
    -0.59
    aurais
    -0.58
    POSITIVE LOGITS
    ChildScrollView
    0.70
    <bos>
    0.66
    ↵↵
    0.65
    ↵
    0.57
    setVerticalGroup
    0.53
    CGRectMake
    0.52
    rungsseite
    0.48
    AddWithValue
    0.48
    KURZBESCHREIBUNG
    0.48
    fjspx
    0.47
    Activations Density 1.943%

    No Known Activations