© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12876
    Prev
    Next
    INDEX
    Explanations

    shell script syntax

    oai_token-act-pair · 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
    omitempty
    -0.54
    Surgical
    -0.50
     SwitchCompat
    -0.50
    ViewFeatures
    -0.49
     Khat
    -0.48
    짝
    -0.48
     InputDecoration
    -0.48
    lossians
    -0.47
     ves
    -0.47
    +#+
    -0.46
    POSITIVE LOGITS
     Monfieur
    0.76
     Anſ
    0.71
     ―――――
    0.69
     ſeveral
    0.69
     ſch
    0.68
     CHAPITRE
    0.68
     bershka
    0.68
     Reſ
    0.66
     Cæsar
    0.65
    '],$
    0.63
    Activations Density 2.623%

    No Known Activations