© 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. 9644
    Prev
    Next
    INDEX
    Explanations

    css code snippets and related keywords

    oai_token-act-pair · gemini-2.0-flash

    : and px

    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
    ApiOperation
    -0.54
    lag
    -0.52
     S
    -0.50
    alk
    -0.50
    lambda
    -0.49
    InitVars
    -0.47
    ardy
    -0.47
    GetInt
    -0.46
     Her
    -0.46
    nellement
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.71
     cauſe
    0.66
     purpoſe
    0.65
     reaſon
    0.63
     laſt
    0.62
     RSSSF
    0.60
     poffe
    0.59
     diſt
    0.59
     faſt
    0.59
     houſe
    0.59
    Activations Density 1.618%

    No Known Activations