© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4009
    Prev
    Next
    INDEX
    Explanations

    code snippets with HTTP requests using `axios` or `ajax` in Javascript.

    oai_token-act-pair · gemini-2.0-flash

    say ":" character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Theſe
    -1.11
     himſelf
    -1.02
     Efq
    -1.01
     Monfieur
    -0.98
     Jefus
    -0.95
     themſelves
    -0.92
     greateſt
    -0.91
     myſelf
    -0.91
     ſeveral
    -0.90
     becauſe
    -0.90
    POSITIVE LOGITS
     :
    0.79
    :
    0.68
    ,
    0.60
     ,
    0.54
    <bos>
    0.50
     “
    0.49
     {},
    0.47
    :
    0.45
     "
    0.44
    :{
    0.44
    Activations Density 5.712%

    No Known Activations