© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14245
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to technology, research, and locations.

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     kasarigan
    -0.71
    TagMode
    -0.69
    Билгалдахарш
    -0.68
     الحره
    -0.66
     lenker
    -0.63
    enterOuterAlt
    -0.62
     resourceCulture
    -0.60
     NSCoder
    -0.59
     AudioClip
    -0.59
    =$?
    -0.57
    POSITIVE LOGITS
    Origins
    0.58
     surfaces
    0.54
     interfaces
    0.54
    interfaces
    0.51
     addresses
    0.51
     Surfaces
    0.49
     issue
    0.49
    HasMaxLength
    0.49
    rece
    0.49
     incomes
    0.48
    Activations Density 8.300%

    No Known Activations