© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9114
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothes, especially those given in testimony or interrogation

    oai_token-act-pair · gemini-2.0-flash

    Clothing and fabrics

    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
    AccessorTable
    -1.02
    Portail
    -0.99
    HtmlAttribute
    -0.84
     TextAppearance
    -0.81
    SourceChecksum
    -0.81
     Efq
    -0.81
    出版年
    -0.78
     Shakspeare
    -0.77
     Normdatei
    -0.75
     HasFactory
    -0.75
    POSITIVE LOGITS
     cac
    0.39
     th
    0.39
     YORK
    0.38
     gru
    0.37
     ist
    0.37
     cu
    0.36
     ran
    0.36
     V
    0.36
    **
    0.36
    rd
    0.36
    Activations Density 1.303%

    No Known Activations