© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13365
    Prev
    Next
    INDEX
    Explanations

    adverbs intensifying "far" or other descriptions of an extreme.

    oai_token-act-pair · gemini-2.0-flash

    far

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     ujednoznacz
    -0.78
     يتيمه
    -0.77
    UnknownFields
    -0.73
    DoubleQuotes
    -0.69
    HtmlAttribute
    -0.67
    iastes
    -0.67
    cshtml
    -0.66
    tagHelperRunner
    -0.66
    cipal
    -0.65
     estekak
    -0.63
    POSITIVE LOGITS
     far
    2.89
    far
    2.25
    Far
    2.02
     Far
    1.89
     FAR
    1.66
    FAR
    1.52
     langt
    1.38
     jauh
    1.31
     далеко
    1.28
     weit
    1.24
    Activations Density 2.799%

    No Known Activations