© 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. 3237
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    oai_token-act-pair · gemini-2.0-flash

    opening curly brace

    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
     ten
    -0.52
     pop
    -0.48
    /***/
    -0.48
     Ten
    -0.48
     Dirty
    -0.47
    monium
    -0.47
    pop
    -0.46
    )?;
    -0.45
    ver
    -0.45
     Schatz
    -0.45
    POSITIVE LOGITS
    IUrlHelper
    0.84
    AndEndTag
    0.80
    principalColumn
    0.78
     estekak
    0.76
    Hentet
    0.73
    లాలు
    0.70
     ImportError
    0.66
     saites
    0.64
    Tembelea
    0.63
     وتسجيلات
    0.63
    Activations Density 3.512%

    No Known Activations