© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11174
    Prev
    Next
    INDEX
    Explanations

    latex code to include images

    oai_token-act-pair · gemini-2.0-flash

    includegraphics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    “
    -0.44
    incr
    -0.44
     distinction
    -0.43
    oman
    -0.43
     
    -0.42
    OMAN
    -0.42
     typical
    -0.41
    Total
    -0.41
    گرد
    -0.41
     pó
    -0.40
    POSITIVE LOGITS
     nahilalakip
    1.31
     propOrder
    1.02
    +#+
    0.99
    @[+][
    0.99
    uxxxx
    0.95
     GeoNames
    0.93
    ponses
    0.92
     AssemblyCulture
    0.90
     referenties
    0.90
     kaarangay
    0.90
    Activations Density 1.032%

    No Known Activations