© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7014
    Prev
    Next
    INDEX
    Explanations

    words related to feelings or desires

    oai_token-act-pair · gemini-2.0-flash

    unconventional formatting or symbols

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

    Informal conversational text

    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
    
    -1.19
    expandindo
    -0.94
    MENAFN
    -0.93
    wasn
    -0.92
     &___
    -0.90
    __":
    -0.88
    Lots
    -0.88
    Doesn
    -0.85
    dafx
    -0.85
     grandkids
    -0.85
    POSITIVE LOGITS
    ..
    0.44
     Table
    0.39
     Wo
    0.39
    おも
    0.37
     ni
    0.37
     not
    0.37
     id
    0.37
    ง
    0.37
     cours
    0.36
    おお
    0.36
    Activations Density 4.347%

    No Known Activations