© 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. 8098
    Prev
    Next
    INDEX
    Explanations

    HTML tags, URLs, and code-related terms.

    oai_token-act-pair · gemini-2.0-flash

    code and website markup

    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
     sal
    -0.79
     Sal
    -0.75
    Sal
    -0.63
    sal
    -0.62
    joba
    -0.59
    SAL
    -0.59
    脚注の使い方
    -0.59
    WireFormat
    -0.58
     Car
    -0.57
    car
    -0.57
    POSITIVE LOGITS
    __':
    0.69
    GraphicsUnit
    0.56
     devriez
    0.54
     feroit
    0.53
    (;;)
    0.53
     auroit
    0.51
    uxxxx
    0.51
     démocr
    0.51
    tagHelperRunner
    0.50
     quelcon
    0.49
    Activations Density 5.381%

    No Known Activations