© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9460
    Prev
    Next
    INDEX
    Explanations

    strings of numbers

    oai_token-act-pair · gemini-2.0-flash

    numbers and widths

    np_token-act-pair-logits · gpt-4o-mini

    wide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ThroughAttribute
    -0.74
    ParallelGroup
    -0.70
    DockStyle
    -0.69
    tagHelperRunner
    -0.68
     imageNamed
    -0.68
    sizeCache
    -0.66
    addPreferredGap
    -0.65
     consultato
    -0.63
     مشين
    -0.63
    RegressionTest
    -0.63
    POSITIVE LOGITS
    7
    0.64
     Wide
    0.56
     Max
    0.52
    Wide
    0.52
     Dream
    0.51
     Seventy
    0.48
     wide
    0.47
     narrow
    0.46
    Dream
    0.46
     बो
    0.44
    Activations Density 1.250%

    No Known Activations