© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5212
    Prev
    Next
    INDEX
    Explanations

    text giving a justification for something

    oai_token-act-pair · gemini-2.0-flash

    reason

    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
     nakalista
    -0.68
    URLException
    -0.68
     itſelf
    -0.63
    izations
    -0.62
     referenties
    -0.61
    ,:);
    -0.59
    AutoresizingMask
    -0.59
    "}")
    -0.58
     poffible
    -0.58
    knapp
    -0.58
    POSITIVE LOGITS
    はじめに
    0.73
     AssemblyVersion
    0.59
    CreateModel
    0.56
    Cuántos
    0.54
     préférences
    0.54
     gian
    0.53
     continúas
    0.51
     donc
    0.51
    ристання
    0.50
     Especially
    0.50
    Activations Density 1.005%

    No Known Activations