© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12737
    Prev
    Next
    INDEX
    Explanations

    a mix of things containing numerical formulas, genetics, and related web addresses

    oai_token-act-pair · gemini-2.0-flash

    technical or acronym laden text

    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
     disambiguazione
    -0.59
    ########.
    -0.52
    GHIJKLM
    -0.49
     himo
    -0.46
     darb
    -0.43
     nė
    -0.42
    المناصب
    -0.40
    Erreferentziak
    -0.40
     Wikimedijinoj
    -0.40
    脚注の使い方
    -0.39
    POSITIVE LOGITS
     VA
    1.06
     Vincent
    1.03
     Vernon
    1.02
     Va
    1.00
     Ven
    1.00
     VEN
    0.99
     Vivian
    0.99
    Ven
    0.98
     Valerie
    0.98
     Vel
    0.97
    Activations Density 11.640%

    No Known Activations