Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12221
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to software, services, and companies, especially those related to graphics, hosting, or Amazon Web Services

    oai_token-act-pair · gemini-2.0-flash

    Software and online platforms

    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
    $}}
    -0.68
     дописавши
    -0.63
    RegistryLite
    -0.62
    })$}
    -0.59
    expandindo
    -0.59
    ngdoc
    -0.59
    OrBuilder
    -0.59
    #![
    -0.57
    });
    
    
    -0.57
    );*/
    -0.57
    POSITIVE LOGITS
    Życiorys
    0.47
    łbym
    0.44
    IsContent
    0.42
    Dzień
    0.42
    IndentedString
    0.41
    Witam
    0.40
    culas
    0.40
    ípios
    0.40
    SerializedSize
    0.39
     MenuView
    0.39
    Activations Density 1.433%

    No Known Activations