© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13735
    Prev
    Next
    INDEX
    Explanations

    words commonly used in online advertising

    oai_token-act-pair · gemini-2.0-flash

    random text/spam

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     跳转至
    -0.55
     conmigo
    -0.47
    soka
    -0.45
    SOUNDBITE
    -0.41
    semantics
    -0.40
     Rios
    -0.38
    amh
    -0.38
    wahati
    -0.37
    conia
    -0.37
    assertSame
    -0.36
    POSITIVE LOGITS
     كومونز
    0.89
    الحياه
    0.84
    Portale
    0.81
     Мексичка
    0.75
     Biôgrafia
    0.70
    Попис
    0.69
     otomatig
    0.67
    IsMutable
    0.67
     nahilalakip
    0.66
     الحره
    0.64
    Activations Density 0.970%

    No Known Activations