© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4003
    Prev
    Next
    INDEX
    Explanations

    code and file system directory paths within code

    oai_token-act-pair · gemini-2.0-flash

    coding keywords in programming contexts

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

    programming 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
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.60
     שוליים
    -0.56
     Paglinawan
    -0.47
     autorytatywna
    -0.47
    addCriterion
    -0.43
    ాల
    -0.41
     kaarangay
    -0.41
    degrees
    -0.41
    lowercase
    -0.40
    Predecesor
    -0.39
    POSITIVE LOGITS
    findpost
    0.65
    shadowRadius
    0.63
     Assignment
    0.62
    resave
    0.60
    TintMode
    0.59
    +#+
    0.59
    abestanden
    0.58
    SessionFactory
    0.57
    }>;
    0.57
    السكان
    0.57
    Activations Density 1.168%

    No Known Activations