© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9961
    Prev
    Next
    INDEX
    Explanations

    negative statements related to something that matters

    oai_token-act-pair · gemini-2.0-flash

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     '\\;'
    -0.77
    <bos>
    -0.74
     незавершена
    -0.72
     gynhyrchwyd
    -0.66
    Kjelder
    -0.62
    ItemBackground
    -0.61
    TargetException
    -0.61
     Мексичка
    -0.60
    انيف
    -0.60
    AutoScale
    -0.59
    POSITIVE LOGITS
    halo
    0.48
    inner
    0.47
    λια
    0.46
    hane
    0.46
    фор
    0.46
     Bris
    0.46
     Kost
    0.45
    HasAnnotation
    0.45
     Kal
    0.44
     قب
    0.44
    Activations Density 0.796%

    No Known Activations