© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2979
    Prev
    Next
    INDEX
    Explanations

    code snippets related to function calls in Ruby

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    Negative Logits
    Geplaatst
    -0.93
    LookAnd
    -0.89
     estimés
    -0.85
    invokeLater
    -0.85
    MigrationBuilder
    -0.84
    Personendaten
    -0.82
     дописавши
    -0.81
     Савезне
    -0.76
     BoxFit
    -0.75
    +#+#
    -0.75
    POSITIVE LOGITS
    etje
    0.47
    querySelector
    0.46
    處
    0.44
     heo
    0.44
    ggior
    0.42
    locke
    0.42
    ordo
    0.41
    icylic
    0.40
    BoxShadow
    0.40
    ADI
    0.40
    Activations Density 4.539%

    No Known Activations