© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10120
    Prev
    Next
    INDEX
    Explanations

    language describing statistical analysis of data

    oai_token-act-pair · gemini-2.0-flash

    Quantities and comparison

    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
     فريبيس
    -1.20
     الحره
    -1.13
     Monfieur
    -1.13
     MainAxisSize
    -1.11
     themſelves
    -1.07
     myſelf
    -1.06
     Theſe
    -1.05
     Efq
    -1.05
     transfieras
    -1.02
    MessageOf
    -1.02
    POSITIVE LOGITS
     great
    0.45
    l
    0.40
     il
    0.38
    ll
    0.37
     l
    0.37
    ls
    0.36
     higher
    0.36
     mucha
    0.35
     Gran
    0.35
    lig
    0.35
    Activations Density 7.181%

    No Known Activations