© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8163
    Prev
    Next
    INDEX
    Explanations

    code snippets including the words "states", "state", and "errors"

    oai_token-act-pair · gemini-2.0-flash

    Coding states and objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     plan
    -0.42
     spot
    -0.41
    iny
    -0.40
    cplusplus
    -0.39
     Spot
    -0.38
     Plan
    -0.38
    план
    -0.38
     check
    -0.37
     Mass
    -0.37
     Sc
    -0.36
    POSITIVE LOGITS
    PerformLayout
    0.98
    AccessorTable
    0.85
     Италијани
    0.74
    TintMode
    0.74
    (!__
    0.73
    تقاوى
    0.73
    oredCriteria
    0.71
    AndEndTag
    0.71
    EndGlobalSection
    0.71
    ViewFeatures
    0.70
    Activations Density 1.927%

    No Known Activations