© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6078
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments and related syntax

    oai_token-act-pair · gemini-2.0-flash

    commands or keywords related to left orientation or movement

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    )</
    -1.00
    ?)
    -0.99
    ）
    -0.92
    ！）
    -0.90
     ）
    -0.88
    >)</
    -0.85
    ?).
    -0.85
    !)
    -0.85
    .”)
    -0.85
     )
    -0.83
    POSITIVE LOGITS
    left
    1.12
     left
    0.87
    RenderAtEndOf
    0.68
     laiss
    0.68
    左
    0.66
     Left
    0.66
     مشين
    0.65
     leaves
    0.64
    Left
    0.64
     leave
    0.64
    Activations Density 0.375%

    No Known Activations