© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5653
    Prev
    Next
    INDEX
    Explanations

    mentions of the statistical analysis software SPSS and Bible verses

    oai_token-act-pair · gemini-2.0-flash

    teens and twenties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    mobileqq
    -0.59
    MethodManager
    -0.58
     ujednoznacz
    -0.58
    ExtendWith
    -0.57
     autorytatywna
    -0.57
    terase
    -0.55
    Personendaten
    -0.54
    økt
    -0.53
    EnableWeb
    -0.52
    gameserver
    -0.52
    POSITIVE LOGITS
     nineteenth
    0.77
     eighteen
    0.77
     Eighteen
    0.75
     eighteenth
    0.75
     nineteen
    0.67
     twenty
    0.66
     Nineteenth
    0.65
     twentieth
    0.64
     Twenty
    0.62
     Nineteen
    0.61
    Activations Density 1.916%

    No Known Activations