© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    the word "face" and phrases containing it

    oai_token-act-pair · gemini-2.0-flash

    'face' references and related terms

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

    face

    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
    رشف
    -0.67
     utafitiHapana
    -0.59
     समीक्षक
    -0.58
     Normdatei
    -0.57
    
    -0.56
     незавершена
    -0.56
    äsident
    -0.56
    Datuak
    -0.55
    potranspiration
    -0.54
     sobě
    -0.54
    POSITIVE LOGITS
    adaptiveStyles
    0.75
    FieldBuilder
    0.58
     Fø
    0.52
    보
    0.49
    IActionResult
    0.49
     newBuilder
    0.47
     zd
    0.47
    бли
    0.47
     tur
    0.46
    يح
    0.46
    Activations Density 2.337%

    No Known Activations