© 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. 12691
    Prev
    Next
    INDEX
    Explanations

    text describing an underwater reef with colorful sea life

    oai_token-act-pair · 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
    eckel
    -0.53
    StoryboardSegue
    -0.50
    tagHelperRunner
    -0.46
     WaitForSeconds
    -0.45
    artifactId
    -0.45
     dasarnya
    -0.42
     čer
    -0.42
     calloc
    -0.42
    Packard
    -0.42
    encial
    -0.41
    POSITIVE LOGITS
    migrationBuilder
    0.71
    المشاركات
    0.67
    MessageTagHelper
    0.63
     GenerationType
    0.62
     pinulongan
    0.62
    Demografía
    0.61
    Portale
    0.60
     GlobalKey
    0.60
    RegressionTest
    0.58
    expandindo
    0.57
    Activations Density 0.922%

    No Known Activations