© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4632
    Prev
    Next
    INDEX
    Explanations

    strings in C/C++ code

    oai_token-act-pair · gemini-2.0-flash

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.44
    EDEFAULT
    -1.38
    NUMX
    -1.38
     itſelf
    -1.37
    twimg
    -1.34
     ―――――
    -1.34
     resourceCulture
    -1.34
     Reſ
    -1.32
    DeleteBehavior
    -1.32
    BibitemShut
    -1.30
    POSITIVE LOGITS
    <bos>
    1.07
    ↵
    0.96
    ↵↵
    0.90
    2
    0.86
    (
    0.82
    for
    0.81
    1
    0.79
    in
    0.79
    n
    0.78
    The
    0.77
    Activations Density 0.349%

    No Known Activations