© 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. 11005
    Prev
    Next
    INDEX
    Explanations

    code snippets and environment variables

    oai_token-act-pair · gemini-2.0-flash

    say "quotation marks and parenthesis"

    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
    '.
    -1.24
    `.
    -1.23
    .
    -1.21
    ".
    -1.20
    .
    -1.11
    ’.
    -1.09
     }.
    -1.09
    ().
    -1.07
    '].
    -1.05
    》.
    -1.05
    POSITIVE LOGITS
     ligiloj
    0.61
    tvguidetime
    0.59
    Descripció
    0.58
     meanwhile
    0.57
    véni
    0.57
    setPointSize
    0.56
    writeFieldEnd
    0.56
     toArray
    0.56
    LookAnd
    0.55
     TextAlign
    0.55
    Activations Density 1.041%

    No Known Activations