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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4193
    Prev
    Next
    INDEX
    Explanations

    references to blog posts, and the dates in blog posts

    oai_token-act-pair · gemini-2.0-flash

    blog posts

    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
     posting
    -2.67
     posts
    -2.48
     posted
    -2.47
     Posting
    -2.39
     postings
    -2.30
    Posting
    -2.28
    posted
    -2.22
    posting
    -2.19
     Posts
    -2.14
    posts
    -2.11
    POSITIVE LOGITS
    initializeApp
    0.49
    nativeElement
    0.48
    __':
    0.48
    FromArgb
    0.47
     quả
    0.47
     WebDriver
    0.46
     nghiệm
    0.45
     beneficiaries
    0.44
     Berech
    0.44
    IVAL
    0.43
    Activations Density 2.528%

    No Known Activations