© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15325
    Prev
    Next
    INDEX
    Explanations

    instances where something is lacking

    oai_token-act-pair · gemini-2.0-flash

    Need or lack of something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    SequentialGroup
    -0.80
    parsedMessage
    -0.56
     insuffisamment
    -0.54
    RTGC
    -0.54
     متعلقه
    -0.52
    TypedDataSet
    -0.51
     незавершена
    -0.48
    transQ
    -0.48
    addCriterion
    -0.47
     везе
    -0.46
    POSITIVE LOGITS
    مصادر
    0.79
     scolas
    0.62
     Californie
    0.60
     ejus
    0.59
    čenje
    0.58
     juridiques
    0.58
     casada
    0.57
     countries
    0.56
     manutenzione
    0.56
     podjet
    0.56
    Activations Density 4.244%

    No Known Activations