© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14459
    Prev
    Next
    INDEX
    Explanations

    names of people and locations

    oai_token-act-pair · gemini-2.0-flash

    writing excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ṁ
    -0.50
    GLOBALS
    -0.47
    bouncycastle
    -0.46
    wochen
    -0.45
     cann
    -0.44
    Browsable
    -0.43
     Spart
    -0.43
    IBarButtonItem
    -0.42
     bhp
    -0.42
     []
    -0.42
    POSITIVE LOGITS
    <bos>
    1.18
     مشين
    0.85
     autorytatywna
    0.79
     насељу
    0.69
     виправивши
    0.68
     MainAxisSize
    0.64
    ########.
    0.60
     مرئيه
    0.59
    \{\\
    0.59
     تانيه
    0.59
    Activations Density 3.489%

    No Known Activations