© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15887
    Prev
    Next
    INDEX
    Explanations

    location names and restaurant dish names.

    oai_token-act-pair · gemini-2.0-flash

    Kuala Lumpur tourism and food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     genitori
    -0.74
     autorité
    -0.63
     salvajes
    -0.59
     brilhante
    -0.56
     negativas
    -0.56
    BindingResult
    -0.56
    ритори
    -0.54
     sauvages
    -0.54
     péld
    -0.54
     aisladas
    -0.53
    POSITIVE LOGITS
    InjectAttribute
    0.66
     utafitiHapana
    0.56
     محفوظة
    0.54
     bazaar
    0.53
    原始内容存档于
    0.53
    存于互联网档案馆
    0.52
    WithMany
    0.52
     propOrder
    0.52
    AutoField
    0.51
    +#+#
    0.50
    Activations Density 2.398%

    No Known Activations