© 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. 7352
    Prev
    Next
    INDEX
    Explanations

    words and punctuation indicating prefixes

    oai_token-act-pair · gemini-2.0-flash

    Formal, hyphenated phrases

    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
     kasarigan
    -0.68
    ModelSerializer
    -0.57
     tearDown
    -0.54
    setVerticalGroup
    -0.53
     Rigidbody
    -0.52
    円
    -0.52
     للاسماء
    -0.50
     JScrollPane
    -0.50
    __((
    -0.48
    IntoConstraints
    -0.48
    POSITIVE LOGITS
    ESSMENT
    0.61
    rawtypes
    0.56
     AssemblyCulture
    0.55
    معلومات
    0.55
    chable
    0.54
    UTIVE
    0.53
     Lightboxes
    0.53
     iconFacebook
    0.52
    tled
    0.52
    НГ
    0.52
    Activations Density 5.661%

    No Known Activations