© 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. 7681
    Prev
    Next
    INDEX
    Explanations

    snippets of code along with related discussion

    oai_token-act-pair · gemini-2.0-flash

    program code.Method number: 4, it detects snippets of programming code., program 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
     nakalista
    -0.57
    gogo
    -0.54
    saraba
    -0.53
    ixos
    -0.52
     Horatio
    -0.49
     initComponents
    -0.49
    AnchorStyles
    -0.48
    躇
    -0.47
    dolu
    -0.47
    Hozzáférés
    -0.47
    POSITIVE LOGITS
     has
    0.59
    TagMode
    0.58
    XmlEnum
    0.57
     Has
    0.56
    HasAnnotation
    0.54
     Affiliations
    0.52
     Приступљено
    0.50
     ModelExpression
    0.50
     Lordships
    0.49
    ResumeLayout
    0.49
    Activations Density 3.064%

    No Known Activations