© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13513
    Prev
    Next
    INDEX
    Explanations

    words that often come before or after key words describing a future plan or event or place.

    oai_token-act-pair · gemini-2.0-flash

    open

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     kasarigan
    -0.59
    NullCheck
    -0.58
    AccessorTable
    -0.54
    ignons
    -0.53
    URLException
    -0.53
    rungsseite
    -0.52
    Diweddarwch
    -0.51
    økt
    -0.49
     >=",
    -0.49
    échelle
    -0.48
    POSITIVE LOGITS
     open
    3.48
    open
    3.13
    Open
    3.03
     Open
    3.00
     OPEN
    2.61
    OPEN
    2.42
     offenen
    2.08
     offene
    2.06
     abierto
    1.97
     abierta
    1.91
    Activations Density 6.742%

    No Known Activations