© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11609
    Prev
    Next
    INDEX
    Explanations

    words related to user interfaces, medicine or job qualifications

    oai_token-act-pair · gemini-2.0-flash

    Java Swing and ITU/Medical

    np_max-act · gemini-2.0-flash

    non-English words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Hochspringen
    -0.96
    asgi
    -0.88
     Infórmanos
    -0.82
    igshid
    -0.80
    FunctionFlags
    -0.78
     ModelExpression
    -0.75
     intptr
    -0.75
    NamedQueries
    -0.75
    ControllerAdvice
    -0.75
     surla
    -0.74
    POSITIVE LOGITS
    достатки
    0.60
     તે
    0.59
    …
    0.58
    rüstung
    0.56
    ovatel
    0.55
    OrEqual
    0.54
     originaux
    0.54
    сторія
    0.54
    zőkönyv
    0.53
    yttö
    0.53
    Activations Density 17.838%

    No Known Activations