© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12443
    Prev
    Next
    INDEX
    Explanations

    somewhat aggressively worded advice or requests.

    oai_token-act-pair · gemini-2.0-flash

    Complaints and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     autorytatywna
    -1.16
    expandindo
    -1.05
     Мексичка
    -1.04
    ագրություններ
    -0.94
    endphp
    -0.88
     المعيارى
    -0.88
    Rohy
    -0.86
    CloseOperation
    -0.85
    bootstrapcdn
    -0.84
     onCancelled
    -0.83
    POSITIVE LOGITS
    "
    0.47
    ?
    0.45
     -
    0.44
     
    0.43
     lavor
    0.42
    S
    0.42
    -
    0.41
    A
    0.41
    ke
    0.40
    Hi
    0.40
    Activations Density 11.301%

    No Known Activations