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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1952
    Prev
    Next
    INDEX
    Explanations

    various syntax elements commonly used in programming languages like Java and Javascript

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
     تضيفلها
    -1.34
    WebElementEntity
    -1.25
    oa̍t
    -1.23
     '\\;'
    -1.22
     pinulongan
    -1.20
    SourceChecksum
    -1.20
    protoimpl
    -1.17
     beginnetje
    -1.16
    addContainerGap
    -1.15
    _));
    -1.15
    POSITIVE LOGITS
     camels
    0.23
     meningitis
    0.21
     quæ
    0.19
     myſelf
    0.19
     pleaſure
    0.17
     Shakspeare
    0.17
     habet
    0.17
     alternates
    0.17
     exiles
    0.16
     peasants
    0.16
    Activations Density 3.245%

    No Known Activations