© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11588
    Prev
    Next
    INDEX
    Explanations

    Japanese language related to errors and trying to resolve them in an application

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming constructs

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

    させ

    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
     to
    -0.54
     en
    -0.46
    </em>
    -0.40
     Mac
    -0.40
     ile
    -0.40
     likely
    -0.39
     
    -0.38
    .
    -0.37
     menudo
    -0.37
     or
    -0.36
    POSITIVE LOGITS
     CreateTagHelper
    1.03
     ProtoMessage
    0.96
     Monfieur
    0.93
     nakalista
    0.93
     useAppContext
    0.91
     whoſe
    0.88
     Профиль
    0.86
     ་་
    0.85
     Efq
    0.85
     myſelf
    0.84
    Activations Density 1.001%

    No Known Activations