© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6412
    Prev
    Next
    INDEX
    Explanations

    references to legal and historical documents or events

    oai_token-act-pair · gemini-2.0-flash

    Legal/philosophical doctrines

    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
    ⓧ
    -0.77
     незавершена
    -0.74
    تفصیلات
    -0.67
    djangoproject
    -0.65
    makeConstraints
    -0.65
    ällor
    -0.64
     متعلقه
    -0.63
    Referencias
    -0.62
    adaptiveStyles
    -0.60
     consultato
    -0.59
    POSITIVE LOGITS
     itself
    0.57
    itself
    0.52
     autorytatywna
    0.49
     hvid
    0.46
    Bioaccumulative
    0.46
     Logement
    0.42
    bergement
    0.41
     did
    0.41
    fgets
    0.40
    znac
    0.40
    Activations Density 4.699%

    No Known Activations