© 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. 12132
    Prev
    Next
    INDEX
    Explanations

    segments of text from venue reviews that are complaints or mention problems

    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
    VersionUID
    -0.66
    twimg
    -0.55
    tableFuture
    -0.53
    oredCriteria
    -0.50
     ujednoznacz
    -0.49
     popoli
    -0.47
    orianCalendar
    -0.47
    出版年
    -0.47
    ंदीखरीदारी
    -0.45
    bootstrapcdn
    -0.45
    POSITIVE LOGITS
     The
    0.70
     Right
    0.69
     Front
    0.66
    Portale
    0.63
     Nice
    0.62
     Grounds
    0.60
    gebraucht
    0.59
    OfThe
    0.58
    vito
    0.57
    ઠ
    0.57
    Activations Density 4.157%

    No Known Activations