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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9617
    Prev
    Next
    INDEX
    Explanations

    code, especially enum and database related code

    oai_token-act-pair · gemini-2.0-flash

    Code/programming

    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
     having
    -0.64
    ,
    -0.62
    CloseOperation
    -0.62
    VersionUID
    -0.61
     internetowa
    -0.60
     against
    -0.60
     using
    -0.60
    WithIdentifier
    -0.60
    HasAnnotation
    -0.60
     to
    -0.60
    POSITIVE LOGITS
     UserId
    0.44
     UserDao
    0.41
     Final
    0.41
     Độ
    0.41
     '_'
    0.41
     Degree
    0.41
     CGSize
    0.41
     '-';
    0.40
     Edges
    0.40
     CGPoint
    0.40
    Activations Density 14.147%

    No Known Activations