© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8828
    Prev
    Next
    INDEX
    Explanations

    words common in advertisements selling engineering or internet services

    oai_token-act-pair · gemini-2.0-flash

    Apps and software

    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
     AssemblyCulture
    -0.61
     cort
    -0.55
     Dostupné
    -0.54
    Specifier
    -0.52
    Discriminator
    -0.52
    دانشنامهٔ
    -0.52
    ↘
    -0.50
    rungsseite
    -0.50
     veter
    -0.50
    LEncoder
    -0.50
    POSITIVE LOGITS
     popoli
    0.58
     Issues
    0.56
    Issues
    0.55
     issues
    0.55
    issues
    0.54
     ISSUES
    0.54
    évaluateur
    0.52
    ISSUES
    0.50
     مشين
    0.49
    ktop
    0.48
    Activations Density 0.306%

    No Known Activations