© 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. 5353
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming, especially related to file paths, IDs, and URLs

    oai_token-act-pair · gemini-2.0-flash

    words related to connection and identification

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

    URL and address

    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
     itſelf
    -1.09
     MainAxisSize
    -1.05
     Efq
    -0.99
     myſelf
    -0.98
     themſelves
    -0.96
     Monfieur
    -0.92
     Jefus
    -0.90
     Majefty
    -0.90
     ſche
    -0.89
     purpoſe
    -0.86
    POSITIVE LOGITS
     of
    0.61
    ,
    0.52
     relatifs
    0.49
     identifiés
    0.49
     (
    0.47
    .
    0.47
     enviados
    0.45
     valeurs
    0.44
     we
    0.44
     ("
    0.43
    Activations Density 5.655%

    No Known Activations