© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13678
    Prev
    Next
    INDEX
    Explanations

    the letter Y, sometimes within a word

    oai_token-act-pair · gemini-2.0-flash

    Y

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     direto
    -0.50
     direct
    -0.49
     logistique
    -0.47
    ized
    -0.46
     directo
    -0.45
    ്യ
    -0.44
     Direkt
    -0.43
     directa
    -0.43
    Edi
    -0.42
     kym
    -0.42
    POSITIVE LOGITS
    OGND
    0.81
     OFDb
    0.79
    mybatisplus
    0.76
    Diweddarwch
    0.74
    SBATCH
    0.72
     مرئيه
    0.69
    ArrowToggle
    0.69
     kasarigan
    0.68
    DockStyle
    0.66
     autorytatywna
    0.65
    Activations Density 0.164%

    No Known Activations