© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets related to web sessions

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
    tagHelperRunner
    -0.83
     HasFactory
    -0.81
    AndEndTag
    -0.74
     StatefulWidget
    -0.69
    VIAF
    -0.68
    Havolalar
    -0.68
     AssemblyCulture
    -0.67
    WebVitals
    -0.66
    #+#
    -0.65
    Према
    -0.65
    POSITIVE LOGITS
     para
    0.65
    ad
    0.56
     Para
    0.54
    Para
    0.50
    AddWithValue
    0.49
    es
    0.47
    para
    0.46
     PARA
    0.45
    AD
    0.44
    MLLoader
    0.44
    Activations Density 0.567%

    No Known Activations