© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5316
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express comparisons, conflicts, or dependencies

    oai_token-act-pair · gemini-2.0-flash

    comparative statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     than
    -0.93
     compared
    -0.85
     rather
    -0.76
     versus
    -0.72
     vs
    -0.72
    than
    -0.68
     než
    -0.66
     instead
    -0.66
     dibanding
    -0.65
     decât
    -0.65
    POSITIVE LOGITS
    ionario
    0.64
    Naissance
    0.60
     naselje
    0.57
    期刊论文
    0.56
     noqa
    0.55
    ulties
    0.54
    esez
    0.54
     BoxFit
    0.53
    
    0.52
    CLUD
    0.52
    Activations Density 0.599%

    No Known Activations