© 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. 5422
    Prev
    Next
    INDEX
    Explanations

    the word "left" (often appearing as part of a LaTeX code snippet)

    oai_token-act-pair · gemini-2.0-flash

    left

    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
    RenderAtEndOf
    -0.63
    IUrlHelper
    -0.59
    Datuak
    -0.52
    اریخ
    -0.51
    niosek
    -0.50
    +#+#
    -0.50
    $
    -0.49
    ViewFeatures
    -0.48
    didSet
    -0.48
     
    -0.48
    POSITIVE LOGITS
    awtextra
    0.57
    Portale
    0.53
    RequiresApi
    0.52
     surla
    0.50
     GetEnumerator
    0.50
    ativement
    0.50
    behind
    0.49
     bulunabilir
    0.49
     متعلقه
    0.49
    มอ
    0.47
    Activations Density 0.191%

    No Known Activations