© 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. 12424
    Prev
    Next
    INDEX
    Explanations

    descriptions of apartments or homes

    oai_token-act-pair · gemini-2.0-flash

    house

    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
     <<<<<<<<<<<<<<
    -0.75
    
    -0.65
     ProtoMessage
    -0.65
    NOPQRST
    -0.62
    ковь
    -0.62
    bootstrapcdn
    -0.60
    Pyx
    -0.60
    complexContent
    -0.57
    setVerticalGroup
    -0.55
    PyExc
    -0.55
    POSITIVE LOGITS
    StoreMessageInfo
    0.47
    esModule
    0.45
    httphttps
    0.45
     față
    0.43
     Audiodateien
    0.43
    سطس
    0.43
    phrine
    0.39
     monop
    0.39
     correcta
    0.38
    aarrggbb
    0.38
    Activations Density 0.577%

    No Known Activations