© 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. 4646
    Prev
    Next
    INDEX
    Explanations

    the word "mixed," sometimes along with words indicating attachment.

    oai_token-act-pair · gemini-2.0-flash

    mixed

    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
    <bos>
    -1.37
     للمعارف
    -0.76
    \{\\
    -0.75
    '}>
    -0.68
    SequentialGroup
    -0.65
     Himo
    -0.65
     Abp
    -0.64
     Վերցված
    -0.63
     Профиль
    -0.63
    Datuak
    -0.63
    POSITIVE LOGITS
     démocr
    0.71
     prochaines
    0.68
     citoyens
    0.67
     couverts
    0.66
     médecins
    0.65
     boucles
    0.65
     traditionnelle
    0.65
    aperto
    0.63
     elettrico
    0.63
     sauvages
    0.63
    Activations Density 2.517%

    No Known Activations