© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 928
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, such as "return", "assert", "array", "min", "max".

    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_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
    MemoryWarning
    -0.80
    WebServlet
    -0.75
    ContentAsync
    -0.68
    AddTagHelper
    -0.64
    ?'
    -0.63
    RectangleBorder
    -0.63
    %";
    -0.62
    FTFY
    -0.60
    %?
    -0.60
    ?";
    -0.60
    POSITIVE LOGITS
      
    0.56
    --
    0.50
     mouseY
    0.46
    UnknownFieldSet
    0.46
    värr
    0.44
     suprême
    0.41
    Ź
    0.40
    ->
    0.40
    (`
    0.39
    Tow
    0.39
    Activations Density 5.656%

    No Known Activations