© 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. 1936
    Prev
    Next
    INDEX
    Explanations

    parts of code that contain function names and class declarations

    oai_token-act-pair · gemini-2.0-flash

    punctuation characters

    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
     >=",
    -1.15
     disambiguazione
    -1.10
    Geplaatst
    -1.10
     myſelf
    -1.10
     CreateTagHelper
    -1.07
    AndEndTag
    -1.06
    NUMX
    -1.05
     Monfieur
    -1.03
     pleaſure
    -1.02
     raiſ
    -1.01
    POSITIVE LOGITS
    ​
    0.52
    #
    0.49
    '
    0.47
    %
    0.46
    --
    0.45
    l
    0.45
    â
    0.45
    //
    0.43
    **
    0.40
    …
    0.40
    Activations Density 6.857%

    No Known Activations