© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4783
    Prev
    Next
    INDEX
    Explanations

    words that can be related to research papers, sociology, lifestyle, and medicine

    oai_token-act-pair · gemini-2.0-flash

    research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     combineReducers
    -0.69
    ViewImports
    -0.62
     للمعارف
    -0.58
    Билгалдахарш
    -0.55
    ControllerAdvice
    -0.50
     Constitucional
    -0.49
     infrar
    -0.48
     TestBed
    -0.48
     caliente
    -0.48
     sztu
    -0.47
    POSITIVE LOGITS
     socio
    0.65
     =>
    0.61
    TintMode
    0.59
    insic
    0.59
    rican
    0.57
     peer
    0.56
     Mar
    0.56
    φορ
    0.56
     mode
    0.55
     job
    0.54
    Activations Density 9.528%

    No Known Activations