© 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. 7827
    Prev
    Next
    INDEX
    Explanations

    code excerpts including code syntax such as colons, brackets, and parenthesis, and code-related words such as parameters, element, statements, numbers.

    oai_token-act-pair · gemini-2.0-flash

    code snippets or special characters in programming

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

    Programming language syntax

    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
     spaces
    -1.27
     space
    -1.23
    space
    -1.23
     Spaces
    -1.11
    Spaces
    -1.09
    spaces
    -1.09
     Space
    -1.05
    Space
    -1.04
     SPACE
    -1.04
    SPACE
    -0.98
    POSITIVE LOGITS
     &___
    0.51
    AutoField
    0.51
    BeginContext
    0.47
    ']]
    0.44
    '))
    0.44
    ($__
    0.43
    ")),
    0.43
    ">)</
    0.42
    }}">
    0.42
    +#+
    0.42
    Activations Density 1.723%

    No Known Activations