© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8119
    Prev
    Next
    INDEX
    Explanations

    output from debug logs and code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code, sequences, identifiers

    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
     braccio
    -0.49
    <h2>
    -0.46
        
    -0.46
    1
    -0.46
     ış
    -0.45
    0
    -0.44
     chêne
    -0.43
    <h3>
    -0.43
    CE
    -0.42
    springframework
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.86
     Walkover
    0.82
    AddTagHelper
    0.82
    ValueStyle
    0.82
    Cordialement
    0.81
    antaranya
    0.79
     endwhile
    0.75
    onAttach
    0.75
    ChildScrollView
    0.73
     برانيه
    0.70
    Activations Density 3.115%

    No Known Activations