© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7789
    Prev
    Next
    INDEX
    Explanations

    words with the letter sequences "ian", "Pro", or "rne", along with the numerical values 2 and 7.

    oai_token-act-pair · gemini-2.0-flash

    Specific items (people/objects)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Goul
    -0.52
    UseVisualStyle
    -0.50
    ContentAsync
    -0.50
    пен
    -0.45
     爆
    -0.41
    показания
    -0.40
     Polity
    -0.40
     Cleveland
    -0.39
    Rails
    -0.39
     föruts
    -0.39
    POSITIVE LOGITS
    Datuak
    0.79
     TimeUnit
    0.72
     Barth
    0.69
     ControllerBase
    0.69
    pausal
    0.69
    HomeAsUpEnabled
    0.67
     estekak
    0.66
    IsMutable
    0.66
    resave
    0.66
     Audiodateien
    0.65
    Activations Density 1.357%

    No Known Activations