© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 683
    Prev
    Next
    INDEX
    Explanations

    technical computer language constructs and related text

    oai_token-act-pair · gemini-2.0-flash

    non, utility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    MessageOf
    -0.65
    RetentionPolicy
    -0.65
    VersionUID
    -0.64
    ⓘ
    -0.63
     Theſe
    -0.63
    MemoryWarning
    -0.61
    complexContent
    -0.61
     păr
    -0.59
    principalColumn
    -0.58
     myſelf
    -0.58
    POSITIVE LOGITS
     non
    0.53
     utility
    0.52
     opérateur
    0.50
     combat
    0.47
    non
    0.45
     Non
    0.45
    Utility
    0.44
    Non
    0.44
    utility
    0.42
    ьаж
    0.42
    Activations Density 3.822%

    No Known Activations