© 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. 14881
    Prev
    Next
    INDEX
    Explanations

    terms related to Ubuntu and Debian Linux distributions and URLs

    oai_token-act-pair · gemini-2.0-flash

    Ubuntu/Linux support

    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
     operating
    -0.91
     open
    -0.90
    operating
    -0.89
     Operating
    -0.88
     OPERATING
    -0.84
    open
    -0.80
    Operating
    -0.80
     OPEN
    -0.79
     opér
    -0.77
    Open
    -0.76
    POSITIVE LOGITS
    KommentareTeilen
    0.42
     ImportError
    0.39
     Spor
    0.37
    ByUsername
    0.34
     atomic
    0.34
     Lif
    0.34
     pop
    0.33
    UGU
    0.33
     focal
    0.33
     vatt
    0.33
    Activations Density 0.595%

    No Known Activations