© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12687
    Prev
    Next
    INDEX
    Explanations

    historic text referencing items from the past or the study/publication of such things

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     using
    -0.95
    Using
    -0.84
     Using
    -0.83
     utilisant
    -0.81
     USING
    -0.81
     utilizing
    -0.80
     usando
    -0.79
     باستخدام
    -0.77
     mittels
    -0.76
     menggunakan
    -0.75
    POSITIVE LOGITS
    Personendaten
    0.59
     esternos
    0.52
    ospels
    0.48
    isand
    0.46
    InternalFrame
    0.45
     Allociné
    0.45
     saites
    0.44
     Obrador
    0.44
     duvet
    0.44
     mast
    0.44
    Activations Density 2.100%

    No Known Activations