© 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. 12885
    Prev
    Next
    INDEX
    Explanations

    words indicating obligation, instruction, or necessity

    oai_token-act-pair · gemini-2.0-flash

    formal and technical writing

    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
     form
    -2.00
     Form
    -1.63
    form
    -1.61
    Form
    -1.57
     FORM
    -1.39
     forms
    -1.31
    FORM
    -1.30
     Forms
    -1.25
     forma
    -1.14
    Forms
    -1.13
    POSITIVE LOGITS
     Administrativna
    0.62
    pexpr
    0.50
    schild
    0.49
    vės
    0.46
     متعلقه
    0.46
     Савезне
    0.44
     rosse
    0.44
    resave
    0.44
    dalena
    0.44
    ItemBackground
    0.44
    Activations Density 4.296%

    No Known Activations