© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3870
    Prev
    Next
    INDEX
    Explanations

    fairly common words that precede or define something of significance

    oai_token-act-pair · gemini-2.0-flash

    detailed descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     principle
    -1.11
     assumption
    -1.08
    principle
    -1.04
     factor
    -1.03
     option
    -1.02
    Principle
    -1.02
     Principle
    -1.00
    assumption
    -0.99
     symptom
    -0.97
    option
    -0.96
    POSITIVE LOGITS
     zaken
    0.48
    色々と
    0.44
     věci
    0.43
    ViewImports
    0.43
    Дереккөздер
    0.42
    دانشنامهٔ
    0.41
    fjspx
    0.41
    ResumeLayout
    0.40
    loma
    0.40
     adesi
    0.40
    Activations Density 2.727%

    No Known Activations