© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12926
    Prev
    Next
    INDEX
    Explanations

    location-based articles and statistics

    oai_token-act-pair · gemini-2.0-flash

    Long Island

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     @"/
    -0.86
    GraphicsUnit
    -0.78
    MarshalTo
    -0.67
    $_['
    -0.66
    parsedMessage
    -0.65
    oredCriteria
    -0.65
    PyExc
    -0.65
    ///</
    -0.63
    ließlich
    -0.62
    AccessorTable
    -0.62
    POSITIVE LOGITS
     Long
    1.45
    Long
    1.23
     LONG
    1.01
    LONG
    0.89
     long
    0.82
    long
    0.79
     LI
    0.69
     LIE
    0.65
    长
    0.63
     Monta
    0.63
    Activations Density 2.417%

    No Known Activations