© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6648
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to present results and observations in scientific studies

    oai_token-act-pair · gemini-2.0-flash

    saying something clearly

    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
     clear
    -2.75
    clear
    -2.33
     Clear
    -2.25
    Clear
    -2.13
     CLEAR
    -2.03
     obvious
    -1.79
    CLEAR
    -1.77
     clearest
    -1.72
     clearly
    -1.68
     Clearly
    -1.66
    POSITIVE LOGITS
     الحره
    0.72
    Viited
    0.63
    enderror
    0.59
     AssemblyTitle
    0.58
    SpringBootTest
    0.57
    ItemLayout
    0.56
    djangoproject
    0.56
    Controllo
    0.55
    enumii
    0.55
     GenerationType
    0.54
    Activations Density 6.886%

    No Known Activations