© 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. 8277
    Prev
    Next
    INDEX
    Explanations

    text from an internet relay chat (IRC) and some code

    oai_token-act-pair · gemini-2.0-flash

    Code and chat logs

    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
     betweenstory
    -1.07
     kasarigan
    -0.97
     autorytatywna
    -0.93
     nahilalakip
    -0.92
     esternos
    -0.91
    WebVitals
    -0.91
     صوتيه
    -0.90
    DockStyle
    -0.88
     المعيارى
    -0.86
    AutoScaleMode
    -0.83
    POSITIVE LOGITS
    хь
    0.47
     i
    0.46
     []:
    0.45
     met
    0.45
    冒
    0.43
     
    0.43
     pollution
    0.41
     "
    0.40
     f
    0.40
    OnClickListener
    0.40
    Activations Density 0.325%

    No Known Activations