© 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. 10759
    Prev
    Next
    INDEX
    Explanations

    snippets of Java code

    oai_token-act-pair · gemini-2.0-flash

    code delimiters

    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
    .
    -0.65
    。
    -0.45
    ".
    -0.44
     intptr
    -0.44
    ).
    -0.42
    !
    -0.42
    .[
    -0.41
    >{@
    -0.41
    ?
    -0.41
    Correct
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.84
     gainera
    0.76
    rzost
    0.72
    PageRoute
    0.70
    antaine
    0.70
    AndEndTag
    0.69
     IBOutlet
    0.67
    %</
    0.65
    ientôt
    0.64
    }>
    0.60
    Activations Density 0.582%

    No Known Activations