© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    the word "you", especially when used to address the reader

    oai_token-act-pair · gemini-2.0-flash

    you

    np_max-act · gemini-2.0-flash
    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
     fédé
    -0.78
     TestBed
    -0.76
    Obrázky
    -0.73
     titolata
    -0.73
     daihatsu
    -0.68
     démocr
    -0.68
     universelle
    -0.67
    setVerticalGroup
    -0.67
    Clik
    -0.66
     humaine
    -0.66
    POSITIVE LOGITS
    <bos>
    1.02
    “
    0.56
    "
    0.56
    </i>
    0.55
    dropna
    0.54
     “
    0.54
     "
    0.53
    żeli
    0.53
    '
    0.52
    })*/
    0.49
    Activations Density 0.957%

    No Known Activations