© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13740
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to data collection, software, research papers and environmental areas

    oai_token-act-pair · gemini-2.0-flash

    Formal/technical writing

    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
     >=",
    -0.80
    IsContent
    -0.77
     jsPsych
    -0.77
    WriteTagHelper
    -0.77
    principalTable
    -0.75
     Cæsar
    -0.74
    __":
    -0.73
     виправивши
    -0.72
    GEBURTSDATUM
    -0.70
    rungsseite
    -0.70
    POSITIVE LOGITS
    jor
    0.52
    jaer
    0.46
     Mc
    0.44
     }^{(
    0.43
     seren
    0.43
    cig
    0.43
     Unit
    0.43
     de
    0.42
    シス
    0.42
     na
    0.42
    Activations Density 7.672%

    No Known Activations