© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11346
    Prev
    Next
    INDEX
    Explanations

    the word "likely" and lines of dashes

    oai_token-act-pair · gemini-2.0-flash

    likely

    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
     resourceCulture
    -1.16
    AndEndTag
    -0.89
    Архівовано
    -0.85
     CanadaChoose
    -0.83
    urlpatterns
    -0.82
     فريبيس
    -0.82
    ="#"><
    -0.81
     EconPapers
    -0.79
    HasForeignKey
    -0.79
    Hozzáférés
    -0.77
    POSITIVE LOGITS
     optimised
    0.55
    ↵↵
    0.54
    ↵
    0.54
     recognised
    0.49
     utilising
    0.49
     recognising
    0.49
     esterno
    0.48
     optimise
    0.47
     which
    0.46
     realised
    0.46
    Activations Density 0.570%

    No Known Activations