© 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. 8315
    Prev
    Next
    INDEX
    Explanations

    UI elements from a web page in what appears to be a mix of Russian and English.

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
     einen
    -1.00
    einen
    -0.95
     den
    -0.78
     את
    -0.72
     keinen
    -0.68
     GenerationType
    -0.68
     έναν
    -0.67
     ihren
    -0.67
     την
    -0.66
     Einen
    -0.66
    POSITIVE LOGITS
     فريبيس
    0.70
     стаття
    0.68
    ArrowToggle
    0.60
     linkovi
    0.59
    adaptiveStyles
    0.54
     StatelessWidget
    0.52
     cesta
    0.52
    VIAF
    0.51
     barva
    0.49
     η
    0.49
    Activations Density 0.534%

    No Known Activations