© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14033
    Prev
    Next
    INDEX
    Explanations

    words and phrases about actions that are cyclical or rotational

    oai_token-act-pair · gemini-2.0-flash

    turns and rotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    UrlResolution
    -0.78
     pinulongan
    -0.52
     Audiodateien
    -0.50
     friendship
    -0.50
     sfondo
    -0.49
    XtraBars
    -0.49
    friendship
    -0.49
    aarrggbb
    -0.47
    meability
    -0.46
    SharedDtor
    -0.46
    POSITIVE LOGITS
     StatefulWidget
    0.71
     StatelessWidget
    0.64
     depositphotos
    0.59
    المناصب
    0.58
    交代
    0.57
    uxxxx
    0.56
     ſever
    0.53
    原始内容存档于
    0.52
     inaczej
    0.50
     turno
    0.49
    Activations Density 1.508%

    No Known Activations