© 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. 3479
    Prev
    Next
    INDEX
    Explanations

    Java code annotations and keywords

    oai_token-act-pair · gemini-2.0-flash

    Java class names

    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
    Stain
    -0.54
     easel
    -0.53
     Nunn
    -0.51
     hairy
    -0.50
    SNA
    -0.50
    mallow
    -0.48
    mallows
    -0.48
     NFA
    -0.47
     NC
    -0.47
     glassy
    -0.47
    POSITIVE LOGITS
    GrantedAuthority
    0.73
     JpaRepository
    0.66
    UserRepository
    0.65
    PasswordEncoder
    0.61
    PostConstruct
    0.59
    HttpStatus
    0.58
    ByPrimaryKey
    0.58
    SpringBootTest
    0.58
    XmlAccessType
    0.57
     UserRepository
    0.57
    Activations Density 4.645%

    No Known Activations