© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9048
    Prev
    Next
    INDEX
    Explanations

    code snippets that use object properties, conditional statements or http headers

    oai_token-act-pair · gemini-2.0-flash

    Code variables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Jereo
    -0.86
    :",
    -0.86
     betweenstory
    -0.84
    Personendaten
    -0.83
    :',
    -0.82
     },
    -0.82
    UserScript
    -0.81
    :
    -0.81
    ":
    -0.79
    #
    -0.79
    POSITIVE LOGITS
    uro
    0.43
    empor
    0.42
     Bild
    0.38
    liss
    0.32
     tha
    0.31
    mens
    0.30
    彙
    0.30
     bir
    0.30
     atividade
    0.30
    ttä
    0.29
    Activations Density 1.164%

    No Known Activations