© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11584
    Prev
    Next
    INDEX
    Explanations

    the word "where", as well as words that commonly surround the word "where"

    oai_token-act-pair · gemini-2.0-flash

    where

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     where
    -0.92
    where
    -0.85
    Where
    -0.73
     Where
    -0.73
     WHERE
    -0.69
    :✨
    -0.68
    WHERE
    -0.67
     dónde
    -0.66
    HttpFoundation
    -0.66
     donde
    -0.60
    POSITIVE LOGITS
    IActionResult
    0.49
    nsf
    0.47
     ejecutivo
    0.47
     frontière
    0.47
    ever
    0.47
    انيف
    0.46
    ância
    0.45
    ]._
    0.45
    InThe
    0.44
    से
    0.44
    Activations Density 0.355%

    No Known Activations