© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11740
    Prev
    Next
    INDEX
    Explanations

    sentences about wild horses being taken care of and adopted

    oai_token-act-pair · 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
     חיצוניים
    -0.59
    PRNewswire
    -0.59
     للمعارف
    -0.59
     relatifs
    -0.56
    setCellStyle
    -0.52
     errado
    -0.50
     économiques
    -0.48
    发表于
    -0.48
     cucchiaio
    -0.48
    Experienced
    -0.47
    POSITIVE LOGITS
    AnchorStyles
    0.71
     medic
    0.68
    dafx
    0.65
    OGND
    0.60
    GEBURTSDATUM
    0.59
    StructEnd
    0.58
     betweenstory
    0.57
     newBuilder
    0.57
    ClCompile
    0.56
    SourceChecksum
    0.56
    Activations Density 4.823%

    No Known Activations