© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10323
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to comprehension, observation, and physical interaction within a system or environment.

    oai_token-act-pair · gemini-2.0-flash

    understanding and feelings

    np_max-act · gemini-2.0-flash

    mental states

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     
    -0.45
    ↵↵
    -0.44
     @
    -0.44
     amazing
    -0.43
     "
    -0.42
    reta
    -0.41
     under
    -0.41
    @
    -0.41
    /
    -0.41
     on
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    0.93
    
    0.89
    ագրություններ
    0.87
    TypedDataSet
    0.85
    writeFieldEnd
    0.82
    abetes
    0.82
    WebVitals
    0.80
    下载附件
    0.80
    awtextra
    0.79
     كومونز
    0.77
    Activations Density 2.515%

    No Known Activations