© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6859
    Prev
    Next
    INDEX
    Explanations

    words or phrases that can indicate positive sentiment or evaluation in reviews of products.

    oai_token-act-pair · gemini-2.0-flash

    Comparisons and ratings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    참고
    -0.56
    fab
    -0.55
    ]{
    -0.52
    ual
    -0.49
    Sub
    -0.48
     Sub
    -0.46
    ok
    -0.45
    Damp
    -0.44
    ancy
    -0.44
    Meh
    -0.44
    POSITIVE LOGITS
     Efq
    0.83
     CreateTagHelper
    0.79
    Jereo
    0.74
     للمعارف
    0.73
    ]--;
    0.72
     themſelves
    0.67
    yntaxException
    0.66
     myſelf
    0.65
    Jîn
    0.65
     GetEnumerator
    0.64
    Activations Density 8.023%

    No Known Activations