© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10267
    Prev
    Next
    INDEX
    Explanations

    mentions of health, economics, the internet, and the relationship between a whole and its parts.

    oai_token-act-pair · gemini-2.0-flash

    creating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personendaten
    -0.80
    Combine
    -0.56
     Combine
    -0.54
    ="../../
    -0.46
     davon
    -0.46
    ngOnDestroy
    -0.45
     للمعارف
    -0.44
    ঐ
    -0.44
     initComponents
    -0.44
     combine
    -0.44
    POSITIVE LOGITS
     يتيمه
    0.72
     aspect
    0.59
    finish
    0.57
    djangoproject
    0.57
     Aspect
    0.56
     EconPapers
    0.55
    tieth
    0.53
    ecycle
    0.53
     staff
    0.52
     Roskov
    0.52
    Activations Density 1.111%

    No Known Activations