© 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. 9944
    Prev
    Next
    INDEX
    Explanations

    code snippets of several different programming languages

    oai_token-act-pair · gemini-2.0-flash

    terms related to function calls and code structure

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

    (

    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
     
    -0.48
    ว
    -0.46
    !
    -0.45
    щий
    -0.44
     ב
    -0.43
    чих
    -0.43
    ho
    -0.43
    ~
    -0.42
     ~
    -0.42
     ho
    -0.42
    POSITIVE LOGITS
     Theſe
    1.05
     CreateTagHelper
    1.03
     myſelf
    0.91
     تضيفلها
    0.90
     Monfieur
    0.88
     Jefus
    0.84
    ſelf
    0.84
    batore
    0.83
    ſelves
    0.82
     Audiodateien
    0.81
    Activations Density 3.602%

    No Known Activations