© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11567
    Prev
    Next
    INDEX
    Explanations

    language related to the film industry

    oai_token-act-pair · gemini-2.0-flash

    UTA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     pleaſure
    -0.69
    +#+#
    -0.69
     Wiktionnaire
    -0.68
     Monfieur
    -0.66
     مشين
    -0.66
     يتيمه
    -0.65
    Jereo
    -0.62
    ſelf
    -0.62
     Eſ
    -0.62
     Beſ
    -0.62
    POSITIVE LOGITS
    àu
    0.45
     im
    0.41
     dét
    0.40
     Türkçe
    0.40
    idoo
    0.39
    cı
    0.39
     dita
    0.39
    Климат
    0.39
    AdapterView
    0.39
    Override
    0.38
    Activations Density 0.241%

    No Known Activations