© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15852
    Prev
    Next
    INDEX
    Explanations

    the word "organized" and words frequently near it

    oai_token-act-pair · gemini-2.0-flash

    organized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     démocr
    -0.68
     chré
    -0.63
     sogget
    -0.59
     uș
    -0.58
     soeur
    -0.57
     fédé
    -0.56
     gră
    -0.54
    kriv
    -0.54
     végét
    -0.54
     aéri
    -0.53
    POSITIVE LOGITS
     Савезне
    1.07
    CGRectMake
    1.02
    Hozzáférés
    1.02
    WithIOException
    1.02
     насељу
    0.94
     "..\..\..\
    0.94
    awtextra
    0.93
    Портали
    0.92
    ]--;
    0.91
     disambiguazione
    0.91
    Activations Density 1.702%

    No Known Activations