© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    the word "anyway(s)" and other words of different categories, like gardening, body parts, interfaces and other seemingly unrelated terms

    oai_token-act-pair · gemini-2.0-flash

    anyway

    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
     anyway
    -0.91
    anyway
    -0.82
     ohnehin
    -0.77
     anyways
    -0.68
    Anyway
    -0.68
     Anyway
    -0.66
     sowieso
    -0.59
    uttavia
    -0.58
     base
    -0.57
     saja
    -0.56
    POSITIVE LOGITS
    Geplaatst
    0.81
    SharedDtor
    0.77
     للاسماء
    0.75
     AssemblyProduct
    0.74
    localctx
    0.69
     Normdatei
    0.65
     estekak
    0.65
    DeleteBehavior
    0.64
    ########.
    0.64
     pinulongan
    0.64
    Activations Density 1.507%

    No Known Activations