© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13898
    Prev
    Next
    INDEX
    Explanations

    javascript code that imports libraries

    oai_token-act-pair · gemini-2.0-flash

    Code imports/requires

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     
    -0.60
     I
    -0.50
     ko
    -0.50
     do
    -0.50
     O
    -0.49
     Se
    -0.47
     Q
    -0.47
     me
    -0.46
     Co
    -0.46
     vor
    -0.46
    POSITIVE LOGITS
    (‘
    0.83
     photolibrary
    0.79
    Personensuche
    0.78
    èdia
    0.75
    WebServlet
    0.75
    bestos
    0.75
     ་་
    0.73
     itſelf
    0.73
     Efq
    0.73
    CloseOperation
    0.73
    Activations Density 1.424%

    No Known Activations