© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1713
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to reading files in JSON format

    oai_token-act-pair · gemini-2.0-flash

    programming languages or code structures

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

    Code

    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
    Negative Logits
     Baillargeon
    -0.60
    DebuggerStep
    -0.57
    RemoteException
    -0.57
     onPostExecute
    -0.56
    esModule
    -0.56
    DeleteBehavior
    -0.55
     invokingState
    -0.54
     nakalista
    -0.54
    FALSE
    -0.54
     NgModule
    -0.54
    POSITIVE LOGITS
     mellom
    0.59
     List
    0.55
    File
    0.53
     näytte
    0.53
    List
    0.53
    Color
    0.52
     فريبيس
    0.52
     незавершена
    0.51
     Color
    0.50
     mellem
    0.50
    Activations Density 1.303%

    No Known Activations