© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2451
    Prev
    Next
    INDEX
    Explanations

    section headers, figure tags, table tags, and other labels often found in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    parsing document sections

    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
     quæ
    -0.89
     auffi
    -0.78
     ſch
    -0.71
     geſ
    -0.69
     eſt
    -0.69
     Geſ
    -0.66
     ſich
    -0.65
     pleaſure
    -0.64
     hunne
    -0.64
     tiegħek
    -0.63
    POSITIVE LOGITS
     
    0.81
    WithIOException
    0.73
     I
    0.65
     estekak
    0.62
     लेकर
    0.62
    BeginContext
    0.61
     سكانية
    0.60
    "]();
    0.59
    oredCriteria
    0.59
    دانشنامهٔ
    0.58
    Activations Density 16.429%

    No Known Activations