© 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. 12243
    Prev
    Next
    INDEX
    Explanations

    the prefix "semi" and words implying comparison or contrast

    oai_token-act-pair · gemini-2.0-flash

    semi

    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
     Monfieur
    -0.69
     pleaſure
    -0.69
     buhay
    -0.66
     cikin
    -0.65
     vertes
    -0.63
    entibus
    -0.63
     eorum
    -0.63
    geted
    -0.63
    alike
    -0.62
    tellation
    -0.61
    POSITIVE LOGITS
    SBATCH
    0.76
    FunctionFlags
    0.75
     CreateTagHelper
    0.75
    SourceChecksum
    0.68
    ]-->
    0.68
    ]));
    0.67
    CPtr
    0.64
    '){
    0.63
    Autoritní
    0.62
    contentLoaded
    0.60
    Activations Density 2.552%

    No Known Activations