© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11621
    Prev
    Next
    INDEX
    Explanations

    code syntax and environment variables

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     '
    -0.66
    —
    -0.66
     "
    -0.66
     he
    -0.65
    "
    -0.65
    "]:
    -0.61
    ❞
    -0.60
     Le
    -0.60
    Cyfeiriadau
    -0.60
    ")
    -0.58
    POSITIVE LOGITS
     étoient
    0.88
     démocr
    0.81
     plufieurs
    0.77
     carottes
    0.75
     avoient
    0.75
     fidé
    0.75
     feroit
    0.75
     chré
    0.73
    berdayakan
    0.72
     fédé
    0.70
    Activations Density 2.684%

    No Known Activations