© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1014
    Prev
    Next
    INDEX
    Explanations

    technical content relating to LIDAR and topo/bathymetry

    oai_token-act-pair · gemini-2.0-flash

    print

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    chaik
    -0.59
     tilf
    -0.54
    Doch
    -0.54
     án
    -0.53
    eeper
    -0.52
    IsOptional
    -0.52
    Pathway
    -0.52
     Candel
    -0.50
    odenal
    -0.50
    })*/
    -0.50
    POSITIVE LOGITS
     size
    1.01
    size
    0.95
     SIZE
    0.95
    Size
    0.95
     Size
    0.94
    <bos>
    0.82
     sizes
    0.79
    SIZE
    0.78
     Ukuran
    0.76
    サイズ
    0.75
    Activations Density 1.986%

    No Known Activations