© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13621
    Prev
    Next
    INDEX
    Explanations

    people asking questions for help

    oai_token-act-pair · gemini-2.0-flash

    help requests

    np_max-act-logits · 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
    nunca
    -0.57
     genieten
    -0.56
     näin
    -0.53
     Ecc
    -0.49
    flexGrow
    -0.49
     Nunca
    -0.48
    inck
    -0.48
     négatif
    -0.48
    tvguidetime
    -0.48
     Never
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.86
    Geplaatst
    0.74
    ioutil
    0.68
     typelib
    0.56
     cherchés
    0.55
    Hozzáférés
    0.54
     Roskov
    0.54
    homonymie
    0.53
    UTERS
    0.52
    UnifiedTopology
    0.52
    Activations Density 0.727%

    No Known Activations