© 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. 7535
    Prev
    Next
    INDEX
    Explanations

    political events and actions involving more than one person, as well as words that mean "and".

    oai_token-act-pair · gemini-2.0-flash

    technical terminology

    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
     REDUC
    -0.61
     创建时间
    -0.57
     closing
    -0.57
    REMOV
    -0.57
     Téléchargez
    -0.57
     reduced
    -0.56
     reducing
    -0.56
     think
    -0.56
    destroyed
    -0.55
     Reducing
    -0.55
    POSITIVE LOGITS
     betweenstory
    0.87
    XmlAccessType
    0.69
    ErrUnexpectedEOF
    0.68
    UnusedPrivate
    0.68
    MemoryWarning
    0.65
    StoryboardSegue
    0.64
    ImageContext
    0.64
    DoubleQuotes
    0.64
    Watching
    0.64
     <=",
    0.63
    Activations Density 7.867%

    No Known Activations